< Prev | Home | Model | Random | Next >

Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2480 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 2.1010. Min Range: -2.1010

Max Act: 2.0750. Min Act: -0.1700

Data Index: 4308415 (Open Web Text)

Max Activating Token Index: 223

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.1010. Min Range: -2.1010

Max Act: 2.1010. Min Act: -0.1700

Data Index: 2231559 (Open Web Text)

Max Activating Token Index: 240

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.1010. Min Range: -2.1010

Max Act: 2.0668. Min Act: -0.1700

Data Index: 1794031 (Open Web Text)

Max Activating Token Index: 170

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.1010. Min Range: -2.1010

Max Act: 2.0725. Min Act: -0.1700

Data Index: 3697205 (Open Web Text)

Max Activating Token Index: 598

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.1010. Min Range: -2.1010

Max Act: 2.0678. Min Act: -0.1700

Data Index: 7820072 (Open Web Text)

Max Activating Token Index: 563

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.1010. Min Range: -2.1010

Max Act: 2.0536. Min Act: -0.1700

Data Index: 4479384 (Open Web Text)

Max Activating Token Index: 421

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.1010. Min Range: -2.1010

Max Act: 2.0691. Min Act: -0.1700

Data Index: 1789640 (Open Web Text)

Max Activating Token Index: 669

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.1010. Min Range: -2.1010

Max Act: 2.0164. Min Act: -0.1700

Data Index: 6429617 (Open Web Text)

Max Activating Token Index: 572

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.1010. Min Range: -2.1010

Max Act: 2.0226. Min Act: -0.1700

Data Index: 3835208 (Open Web Text)

Max Activating Token Index: 563

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.1010. Min Range: -2.1010

Max Act: 2.0395. Min Act: -0.1700

Data Index: 4675485 (Open Web Text)

Max Activating Token Index: 675

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.1010. Min Range: -2.1010

Max Act: 2.0174. Min Act: -0.1700

Data Index: 2795098 (Open Web Text)

Max Activating Token Index: 762

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.1010. Min Range: -2.1010

Max Act: 2.0216. Min Act: -0.1700

Data Index: 6750181 (Open Web Text)

Max Activating Token Index: 870

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.1010. Min Range: -2.1010

Max Act: 2.0152. Min Act: -0.1700

Data Index: 5734512 (Open Web Text)

Max Activating Token Index: 683

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.1010. Min Range: -2.1010

Max Act: 1.9993. Min Act: -0.1700

Data Index: 8766888 (Open Web Text)

Max Activating Token Index: 416

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.1010. Min Range: -2.1010

Max Act: 1.9917. Min Act: -0.1700

Data Index: 6248352 (Open Web Text)

Max Activating Token Index: 777

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.1010. Min Range: -2.1010

Max Act: 2.0253. Min Act: -0.1700

Data Index: 469782 (Open Web Text)

Max Activating Token Index: 285

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.1010. Min Range: -2.1010

Max Act: 2.0109. Min Act: -0.1700

Data Index: 2601784 (Open Web Text)

Max Activating Token Index: 641

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.1010. Min Range: -2.1010

Max Act: 1.9836. Min Act: -0.1700

Data Index: 6348682 (Open Web Text)

Max Activating Token Index: 695

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.1010. Min Range: -2.1010

Max Act: 1.9951. Min Act: -0.1700

Data Index: 3701661 (Open Web Text)

Max Activating Token Index: 768

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.1010. Min Range: -2.1010

Max Act: 1.9899. Min Act: -0.1700

Data Index: 5457787 (Open Web Text)

Max Activating Token Index: 813

Click toggle to see full text

Truncated

Full Text #19