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

Dataset: Open Web Text

Neuron 2173 in Layer 3

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: 4.5138. Min Range: -4.5138

Max Act: 4.5138. Min Act: -0.1700

Data Index: 335718 (Open Web Text)

Max Activating Token Index: 586

Text #1

Max Range: 4.5138. Min Range: -4.5138

Max Act: 4.4273. Min Act: -0.1700

Data Index: 2160471 (Open Web Text)

Max Activating Token Index: 431

Text #2

Max Range: 4.5138. Min Range: -4.5138

Max Act: 4.4517. Min Act: -0.1700

Data Index: 6616752 (Open Web Text)

Max Activating Token Index: 883

Text #3

Max Range: 4.5138. Min Range: -4.5138

Max Act: 4.3443. Min Act: -0.1700

Data Index: 8051612 (Open Web Text)

Max Activating Token Index: 133

Text #4

Max Range: 4.5138. Min Range: -4.5138

Max Act: 4.2662. Min Act: -0.1700

Data Index: 2888841 (Open Web Text)

Max Activating Token Index: 919

Text #5

Max Range: 4.5138. Min Range: -4.5138

Max Act: 4.3135. Min Act: -0.1700

Data Index: 575644 (Open Web Text)

Max Activating Token Index: 979

Text #6

Max Range: 4.5138. Min Range: -4.5138

Max Act: 4.2951. Min Act: -0.1700

Data Index: 2660576 (Open Web Text)

Max Activating Token Index: 81

Text #7

Max Range: 4.5138. Min Range: -4.5138

Max Act: 4.2501. Min Act: -0.1700

Data Index: 5726220 (Open Web Text)

Max Activating Token Index: 263

Text #8

Max Range: 4.5138. Min Range: -4.5138

Max Act: 4.2367. Min Act: -0.1700

Data Index: 2799979 (Open Web Text)

Max Activating Token Index: 849

Text #9

Max Range: 4.5138. Min Range: -4.5138

Max Act: 4.1881. Min Act: -0.1700

Data Index: 7051015 (Open Web Text)

Max Activating Token Index: 17

Text #10

Max Range: 4.5138. Min Range: -4.5138

Max Act: 4.1844. Min Act: -0.1700

Data Index: 7254425 (Open Web Text)

Max Activating Token Index: 482

Text #11

Max Range: 4.5138. Min Range: -4.5138

Max Act: 4.1451. Min Act: -0.1700

Data Index: 6214977 (Open Web Text)

Max Activating Token Index: 39

Text #12

Max Range: 4.5138. Min Range: -4.5138

Max Act: 4.1551. Min Act: -0.1700

Data Index: 4677246 (Open Web Text)

Max Activating Token Index: 192

Text #13

Max Range: 4.5138. Min Range: -4.5138

Max Act: 4.1350. Min Act: -0.1700

Data Index: 6475140 (Open Web Text)

Max Activating Token Index: 66

Text #14

Max Range: 4.5138. Min Range: -4.5138

Max Act: 4.1534. Min Act: -0.1700

Data Index: 1202395 (Open Web Text)

Max Activating Token Index: 817

Text #15

Max Range: 4.5138. Min Range: -4.5138

Max Act: 4.1154. Min Act: -0.1700

Data Index: 3992838 (Open Web Text)

Max Activating Token Index: 461

Text #16

Max Range: 4.5138. Min Range: -4.5138

Max Act: 4.1065. Min Act: -0.1700

Data Index: 5515343 (Open Web Text)

Max Activating Token Index: 462

Text #17

Max Range: 4.5138. Min Range: -4.5138

Max Act: 4.1209. Min Act: -0.1700

Data Index: 3919762 (Open Web Text)

Max Activating Token Index: 26

Text #18

Max Range: 4.5138. Min Range: -4.5138

Max Act: 4.1193. Min Act: -0.1700

Data Index: 8447993 (Open Web Text)

Max Activating Token Index: 316

Text #19

Max Range: 4.5138. Min Range: -4.5138

Max Act: 4.1035. Min Act: -0.1700

Data Index: 5580816 (Open Web Text)

Max Activating Token Index: 370