< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2007 in Layer 4

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: 2.9914. Min Range: -2.9914

Max Act: 2.9914. Min Act: -0.1700

Data Index: 6396192 (Open Web Text)

Max Activating Token Index: 425

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.9914. Min Range: -2.9914

Max Act: 2.8809. Min Act: -0.1700

Data Index: 291485 (Open Web Text)

Max Activating Token Index: 538

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.9914. Min Range: -2.9914

Max Act: 2.8204. Min Act: -0.1700

Data Index: 3779690 (Open Web Text)

Max Activating Token Index: 242

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.9914. Min Range: -2.9914

Max Act: 2.7940. Min Act: -0.1700

Data Index: 6035049 (Open Web Text)

Max Activating Token Index: 747

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.9914. Min Range: -2.9914

Max Act: 2.7906. Min Act: -0.1700

Data Index: 1167754 (Open Web Text)

Max Activating Token Index: 921

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.9914. Min Range: -2.9914

Max Act: 2.7679. Min Act: -0.1700

Data Index: 1046977 (Open Web Text)

Max Activating Token Index: 391

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.9914. Min Range: -2.9914

Max Act: 2.7805. Min Act: -0.1700

Data Index: 5988724 (Open Web Text)

Max Activating Token Index: 484

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.9914. Min Range: -2.9914

Max Act: 2.7641. Min Act: -0.1700

Data Index: 5533642 (Open Web Text)

Max Activating Token Index: 138

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.9914. Min Range: -2.9914

Max Act: 2.7799. Min Act: -0.1700

Data Index: 7778579 (Open Web Text)

Max Activating Token Index: 287

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.9914. Min Range: -2.9914

Max Act: 2.7472. Min Act: -0.1700

Data Index: 2919486 (Open Web Text)

Max Activating Token Index: 958

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.9914. Min Range: -2.9914

Max Act: 2.7503. Min Act: -0.1700

Data Index: 5124144 (Open Web Text)

Max Activating Token Index: 321

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.9914. Min Range: -2.9914

Max Act: 2.7281. Min Act: -0.1700

Data Index: 2523652 (Open Web Text)

Max Activating Token Index: 91

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.9914. Min Range: -2.9914

Max Act: 2.7233. Min Act: -0.1700

Data Index: 2936500 (Open Web Text)

Max Activating Token Index: 474

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.9914. Min Range: -2.9914

Max Act: 2.7397. Min Act: -0.1700

Data Index: 3531650 (Open Web Text)

Max Activating Token Index: 932

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.9914. Min Range: -2.9914

Max Act: 2.7199. Min Act: -0.1700

Data Index: 8363600 (Open Web Text)

Max Activating Token Index: 359

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.9914. Min Range: -2.9914

Max Act: 2.7329. Min Act: -0.1700

Data Index: 6150866 (Open Web Text)

Max Activating Token Index: 960

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.9914. Min Range: -2.9914

Max Act: 2.7079. Min Act: -0.1700

Data Index: 873826 (Open Web Text)

Max Activating Token Index: 552

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.9914. Min Range: -2.9914

Max Act: 2.7401. Min Act: -0.1700

Data Index: 2116014 (Open Web Text)

Max Activating Token Index: 464

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.9914. Min Range: -2.9914

Max Act: 2.7210. Min Act: -0.1700

Data Index: 7758997 (Open Web Text)

Max Activating Token Index: 143

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.9914. Min Range: -2.9914

Max Act: 2.7262. Min Act: -0.1700

Data Index: 4477771 (Open Web Text)

Max Activating Token Index: 1009

Click toggle to see full text

Truncated

Full Text #19