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

Dataset: Open Web Text

Neuron 233 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: 3.6136. Min Range: -3.6136

Max Act: 3.6136. Min Act: -0.1700

Data Index: 1693460 (Open Web Text)

Max Activating Token Index: 801

Text #1

Max Range: 3.6136. Min Range: -3.6136

Max Act: 3.5202. Min Act: -0.1700

Data Index: 2214001 (Open Web Text)

Max Activating Token Index: 543

Text #2

Max Range: 3.6136. Min Range: -3.6136

Max Act: 3.5275. Min Act: -0.1700

Data Index: 7563292 (Open Web Text)

Max Activating Token Index: 935

Text #3

Max Range: 3.6136. Min Range: -3.6136

Max Act: 3.5375. Min Act: -0.1700

Data Index: 1143132 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 3.6136. Min Range: -3.6136

Max Act: 3.5024. Min Act: -0.1700

Data Index: 3378023 (Open Web Text)

Max Activating Token Index: 773

Text #5

Max Range: 3.6136. Min Range: -3.6136

Max Act: 3.4352. Min Act: -0.1700

Data Index: 728629 (Open Web Text)

Max Activating Token Index: 934

Text #6

Max Range: 3.6136. Min Range: -3.6136

Max Act: 3.4721. Min Act: -0.1700

Data Index: 7025250 (Open Web Text)

Max Activating Token Index: 379

Text #7

Max Range: 3.6136. Min Range: -3.6136

Max Act: 3.4329. Min Act: -0.1700

Data Index: 984558 (Open Web Text)

Max Activating Token Index: 361

Text #8

Max Range: 3.6136. Min Range: -3.6136

Max Act: 3.4493. Min Act: -0.1700

Data Index: 2882022 (Open Web Text)

Max Activating Token Index: 417

Text #9

Max Range: 3.6136. Min Range: -3.6136

Max Act: 3.4484. Min Act: -0.1700

Data Index: 2648999 (Open Web Text)

Max Activating Token Index: 881

Text #10

Max Range: 3.6136. Min Range: -3.6136

Max Act: 3.4333. Min Act: -0.1700

Data Index: 1742150 (Open Web Text)

Max Activating Token Index: 187

Text #11

Max Range: 3.6136. Min Range: -3.6136

Max Act: 3.4237. Min Act: -0.1700

Data Index: 6604863 (Open Web Text)

Max Activating Token Index: 613

Text #12

Max Range: 3.6136. Min Range: -3.6136

Max Act: 3.4224. Min Act: -0.1700

Data Index: 6219435 (Open Web Text)

Max Activating Token Index: 50

Text #13

Max Range: 3.6136. Min Range: -3.6136

Max Act: 3.4159. Min Act: -0.1700

Data Index: 7699339 (Open Web Text)

Max Activating Token Index: 751

Text #14

Max Range: 3.6136. Min Range: -3.6136

Max Act: 3.4508. Min Act: -0.1700

Data Index: 4965402 (Open Web Text)

Max Activating Token Index: 844

Text #15

Max Range: 3.6136. Min Range: -3.6136

Max Act: 3.3987. Min Act: -0.1700

Data Index: 7791443 (Open Web Text)

Max Activating Token Index: 69

Text #16

Max Range: 3.6136. Min Range: -3.6136

Max Act: 3.4213. Min Act: -0.1700

Data Index: 8315282 (Open Web Text)

Max Activating Token Index: 707

Text #17

Max Range: 3.6136. Min Range: -3.6136

Max Act: 3.4447. Min Act: -0.1700

Data Index: 506007 (Open Web Text)

Max Activating Token Index: 496

Text #18

Max Range: 3.6136. Min Range: -3.6136

Max Act: 3.4008. Min Act: -0.1700

Data Index: 7432535 (Open Web Text)

Max Activating Token Index: 639

Text #19

Max Range: 3.6136. Min Range: -3.6136

Max Act: 3.4075. Min Act: -0.1700

Data Index: 375715 (Open Web Text)

Max Activating Token Index: 607