< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 1730 in Layer 6

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: 2.6754. Min Range: -2.6754

Max Act: 2.6754. Min Act: -0.1700

Data Index: 1702105 (Open Web Text)

Max Activating Token Index: 476

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.6754. Min Range: -2.6754

Max Act: 2.6365. Min Act: -0.1700

Data Index: 343446 (Open Web Text)

Max Activating Token Index: 595

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.6754. Min Range: -2.6754

Max Act: 2.6164. Min Act: -0.1700

Data Index: 8610603 (Open Web Text)

Max Activating Token Index: 817

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.6754. Min Range: -2.6754

Max Act: 2.5763. Min Act: -0.1700

Data Index: 5152506 (Open Web Text)

Max Activating Token Index: 434

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.6754. Min Range: -2.6754

Max Act: 2.5654. Min Act: -0.1700

Data Index: 4743989 (Open Web Text)

Max Activating Token Index: 635

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.6754. Min Range: -2.6754

Max Act: 2.5677. Min Act: -0.1700

Data Index: 299316 (Open Web Text)

Max Activating Token Index: 355

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.6754. Min Range: -2.6754

Max Act: 2.5505. Min Act: -0.1700

Data Index: 2331924 (Open Web Text)

Max Activating Token Index: 1000

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.6754. Min Range: -2.6754

Max Act: 2.5461. Min Act: -0.1700

Data Index: 419775 (Open Web Text)

Max Activating Token Index: 73

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.6754. Min Range: -2.6754

Max Act: 2.5425. Min Act: -0.1700

Data Index: 1300393 (Open Web Text)

Max Activating Token Index: 685

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.6754. Min Range: -2.6754

Max Act: 2.5357. Min Act: -0.1700

Data Index: 1407791 (Open Web Text)

Max Activating Token Index: 1016

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.6754. Min Range: -2.6754

Max Act: 2.5219. Min Act: -0.1700

Data Index: 4897704 (Open Web Text)

Max Activating Token Index: 793

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.6754. Min Range: -2.6754

Max Act: 2.5020. Min Act: -0.1700

Data Index: 6826531 (Open Web Text)

Max Activating Token Index: 67

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.6754. Min Range: -2.6754

Max Act: 2.5206. Min Act: -0.1700

Data Index: 4828224 (Open Web Text)

Max Activating Token Index: 74

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.6754. Min Range: -2.6754

Max Act: 2.5113. Min Act: -0.1700

Data Index: 6669491 (Open Web Text)

Max Activating Token Index: 500

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.6754. Min Range: -2.6754

Max Act: 2.4867. Min Act: -0.1700

Data Index: 4195272 (Open Web Text)

Max Activating Token Index: 254

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.6754. Min Range: -2.6754

Max Act: 2.4926. Min Act: -0.1700

Data Index: 2486219 (Open Web Text)

Max Activating Token Index: 482

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.6754. Min Range: -2.6754

Max Act: 2.4851. Min Act: -0.1700

Data Index: 4858090 (Open Web Text)

Max Activating Token Index: 783

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.6754. Min Range: -2.6754

Max Act: 2.5006. Min Act: -0.1700

Data Index: 5436080 (Open Web Text)

Max Activating Token Index: 132

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.6754. Min Range: -2.6754

Max Act: 2.4742. Min Act: -0.1700

Data Index: 6550092 (Open Web Text)

Max Activating Token Index: 779

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.6754. Min Range: -2.6754

Max Act: 2.4790. Min Act: -0.1700

Data Index: 3360076 (Open Web Text)

Max Activating Token Index: 870

Click toggle to see full text

Truncated

Full Text #19