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

Dataset: Open Web Text

Neuron 2701 in Layer 5

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: 2.6492. Min Range: -2.6492

Max Act: 2.6492. Min Act: -0.1700

Data Index: 4262047 (Open Web Text)

Max Activating Token Index: 973

Text #1

Max Range: 2.6492. Min Range: -2.6492

Max Act: 2.5163. Min Act: -0.1700

Data Index: 8565553 (Open Web Text)

Max Activating Token Index: 648

Text #2

Max Range: 2.6492. Min Range: -2.6492

Max Act: 2.5181. Min Act: -0.1699

Data Index: 5619406 (Open Web Text)

Max Activating Token Index: 614

Text #3

Max Range: 2.6492. Min Range: -2.6492

Max Act: 2.4703. Min Act: -0.1700

Data Index: 280686 (Open Web Text)

Max Activating Token Index: 961

Text #4

Max Range: 2.6492. Min Range: -2.6492

Max Act: 2.4751. Min Act: -0.1700

Data Index: 494174 (Open Web Text)

Max Activating Token Index: 887

Text #5

Max Range: 2.6492. Min Range: -2.6492

Max Act: 2.4088. Min Act: -0.1697

Data Index: 4664561 (Open Web Text)

Max Activating Token Index: 701

Text #6

Max Range: 2.6492. Min Range: -2.6492

Max Act: 2.3953. Min Act: -0.1700

Data Index: 2708649 (Open Web Text)

Max Activating Token Index: 635

Text #7

Max Range: 2.6492. Min Range: -2.6492

Max Act: 2.4068. Min Act: -0.1700

Data Index: 1382886 (Open Web Text)

Max Activating Token Index: 940

Text #8

Max Range: 2.6492. Min Range: -2.6492

Max Act: 2.3963. Min Act: -0.1686

Data Index: 3842991 (Open Web Text)

Max Activating Token Index: 453

Text #9

Max Range: 2.6492. Min Range: -2.6492

Max Act: 2.4148. Min Act: -0.1652

Data Index: 6683344 (Open Web Text)

Max Activating Token Index: 724

Text #10

Max Range: 2.6492. Min Range: -2.6492

Max Act: 2.3777. Min Act: -0.1700

Data Index: 5324367 (Open Web Text)

Max Activating Token Index: 176

Text #11

Max Range: 2.6492. Min Range: -2.6492

Max Act: 2.3563. Min Act: -0.1700

Data Index: 937099 (Open Web Text)

Max Activating Token Index: 326

Text #12

Max Range: 2.6492. Min Range: -2.6492

Max Act: 2.3554. Min Act: -0.1700

Data Index: 3869688 (Open Web Text)

Max Activating Token Index: 203

Text #13

Max Range: 2.6492. Min Range: -2.6492

Max Act: 2.3627. Min Act: -0.1700

Data Index: 4262048 (Open Web Text)

Max Activating Token Index: 669

Text #14

Max Range: 2.6492. Min Range: -2.6492

Max Act: 2.3712. Min Act: -0.1700

Data Index: 881991 (Open Web Text)

Max Activating Token Index: 332

Text #15

Max Range: 2.6492. Min Range: -2.6492

Max Act: 2.3616. Min Act: -0.1700

Data Index: 4044031 (Open Web Text)

Max Activating Token Index: 765

Text #16

Max Range: 2.6492. Min Range: -2.6492

Max Act: 2.3432. Min Act: -0.1700

Data Index: 2145605 (Open Web Text)

Max Activating Token Index: 443

Text #17

Max Range: 2.6492. Min Range: -2.6492

Max Act: 2.3474. Min Act: -0.1700

Data Index: 6421908 (Open Web Text)

Max Activating Token Index: 915

Text #18

Max Range: 2.6492. Min Range: -2.6492

Max Act: 2.3385. Min Act: -0.1700

Data Index: 2185629 (Open Web Text)

Max Activating Token Index: 793

Text #19

Max Range: 2.6492. Min Range: -2.6492

Max Act: 2.3331. Min Act: -0.1699

Data Index: 7167245 (Open Web Text)

Max Activating Token Index: 432