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

Dataset: Open Web Text

Neuron 1995 in Layer 1

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: 1.7437. Min Range: -1.7437

Max Act: 1.7437. Min Act: -0.1700

Data Index: 2058164 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 1.7437. Min Range: -1.7437

Max Act: 1.7120. Min Act: -0.1700

Data Index: 4137453 (Open Web Text)

Max Activating Token Index: 983

Text #2

Max Range: 1.7437. Min Range: -1.7437

Max Act: 1.7000. Min Act: -0.1700

Data Index: 6632425 (Open Web Text)

Max Activating Token Index: 516

Text #3

Max Range: 1.7437. Min Range: -1.7437

Max Act: 1.6855. Min Act: -0.1700

Data Index: 4792668 (Open Web Text)

Max Activating Token Index: 267

Text #4

Max Range: 1.7437. Min Range: -1.7437

Max Act: 1.6723. Min Act: -0.1700

Data Index: 6323690 (Open Web Text)

Max Activating Token Index: 469

Text #5

Max Range: 1.7437. Min Range: -1.7437

Max Act: 1.6766. Min Act: -0.1700

Data Index: 2949212 (Open Web Text)

Max Activating Token Index: 553

Text #6

Max Range: 1.7437. Min Range: -1.7437

Max Act: 1.6703. Min Act: -0.1700

Data Index: 4481740 (Open Web Text)

Max Activating Token Index: 154

Text #7

Max Range: 1.7437. Min Range: -1.7437

Max Act: 1.6770. Min Act: -0.1697

Data Index: 6632419 (Open Web Text)

Max Activating Token Index: 264

Text #8

Max Range: 1.7437. Min Range: -1.7437

Max Act: 1.6638. Min Act: -0.1700

Data Index: 8289093 (Open Web Text)

Max Activating Token Index: 183

Text #9

Max Range: 1.7437. Min Range: -1.7437

Max Act: 1.6683. Min Act: -0.1700

Data Index: 6632420 (Open Web Text)

Max Activating Token Index: 98

Text #10

Max Range: 1.7437. Min Range: -1.7437

Max Act: 1.6587. Min Act: -0.1700

Data Index: 8614686 (Open Web Text)

Max Activating Token Index: 592

Text #11

Max Range: 1.7437. Min Range: -1.7437

Max Act: 1.6562. Min Act: -0.1700

Data Index: 5075734 (Open Web Text)

Max Activating Token Index: 730

Text #12

Max Range: 1.7437. Min Range: -1.7437

Max Act: 1.6603. Min Act: -0.1700

Data Index: 1917974 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 1.7437. Min Range: -1.7437

Max Act: 1.6484. Min Act: -0.1700

Data Index: 5235524 (Open Web Text)

Max Activating Token Index: 658

Text #14

Max Range: 1.7437. Min Range: -1.7437

Max Act: 1.6517. Min Act: -0.1700

Data Index: 5839086 (Open Web Text)

Max Activating Token Index: 738

Text #15

Max Range: 1.7437. Min Range: -1.7437

Max Act: 1.6517. Min Act: -0.1700

Data Index: 4714397 (Open Web Text)

Max Activating Token Index: 723

Text #16

Max Range: 1.7437. Min Range: -1.7437

Max Act: 1.6456. Min Act: -0.1700

Data Index: 4563031 (Open Web Text)

Max Activating Token Index: 574

Text #17

Max Range: 1.7437. Min Range: -1.7437

Max Act: 1.6505. Min Act: -0.1700

Data Index: 8079486 (Open Web Text)

Max Activating Token Index: 241

Text #18

Max Range: 1.7437. Min Range: -1.7437

Max Act: 1.6492. Min Act: -0.1700

Data Index: 6685534 (Open Web Text)

Max Activating Token Index: 11

Text #19

Max Range: 1.7437. Min Range: -1.7437

Max Act: 1.6491. Min Act: -0.1700

Data Index: 11562 (Open Web Text)

Max Activating Token Index: 429