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

Dataset: Open Web Text

Neuron 2622 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: 4.5228. Min Range: -4.5228

Max Act: 4.5228. Min Act: -0.1700

Data Index: 5684918 (Open Web Text)

Max Activating Token Index: 643

Text #1

Max Range: 4.5228. Min Range: -4.5228

Max Act: 4.4179. Min Act: -0.1700

Data Index: 4422021 (Open Web Text)

Max Activating Token Index: 364

Text #2

Max Range: 4.5228. Min Range: -4.5228

Max Act: 4.3873. Min Act: -0.1700

Data Index: 151275 (Open Web Text)

Max Activating Token Index: 577

Text #3

Max Range: 4.5228. Min Range: -4.5228

Max Act: 4.4203. Min Act: -0.1700

Data Index: 7409564 (Open Web Text)

Max Activating Token Index: 33

Text #4

Max Range: 4.5228. Min Range: -4.5228

Max Act: 4.3557. Min Act: -0.1700

Data Index: 7990300 (Open Web Text)

Max Activating Token Index: 425

Text #5

Max Range: 4.5228. Min Range: -4.5228

Max Act: 4.3737. Min Act: -0.1700

Data Index: 5359221 (Open Web Text)

Max Activating Token Index: 182

Text #6

Max Range: 4.5228. Min Range: -4.5228

Max Act: 4.3944. Min Act: -0.1700

Data Index: 7960305 (Open Web Text)

Max Activating Token Index: 127

Text #7

Max Range: 4.5228. Min Range: -4.5228

Max Act: 4.3872. Min Act: -0.1700

Data Index: 1695420 (Open Web Text)

Max Activating Token Index: 526

Text #8

Max Range: 4.5228. Min Range: -4.5228

Max Act: 4.3185. Min Act: -0.1700

Data Index: 7030138 (Open Web Text)

Max Activating Token Index: 94

Text #9

Max Range: 4.5228. Min Range: -4.5228

Max Act: 4.3140. Min Act: -0.1700

Data Index: 7959871 (Open Web Text)

Max Activating Token Index: 108

Text #10

Max Range: 4.5228. Min Range: -4.5228

Max Act: 4.3346. Min Act: -0.1700

Data Index: 7312025 (Open Web Text)

Max Activating Token Index: 318

Text #11

Max Range: 4.5228. Min Range: -4.5228

Max Act: 4.3520. Min Act: -0.1700

Data Index: 3457546 (Open Web Text)

Max Activating Token Index: 98

Text #12

Max Range: 4.5228. Min Range: -4.5228

Max Act: 4.3210. Min Act: -0.1700

Data Index: 4392371 (Open Web Text)

Max Activating Token Index: 58

Text #13

Max Range: 4.5228. Min Range: -4.5228

Max Act: 4.3707. Min Act: -0.1700

Data Index: 2898798 (Open Web Text)

Max Activating Token Index: 170

Text #14

Max Range: 4.5228. Min Range: -4.5228

Max Act: 4.3565. Min Act: -0.1700

Data Index: 6957027 (Open Web Text)

Max Activating Token Index: 428

Text #15

Max Range: 4.5228. Min Range: -4.5228

Max Act: 4.3284. Min Act: -0.1700

Data Index: 1688084 (Open Web Text)

Max Activating Token Index: 336

Text #16

Max Range: 4.5228. Min Range: -4.5228

Max Act: 4.3262. Min Act: -0.1700

Data Index: 4989619 (Open Web Text)

Max Activating Token Index: 66

Text #17

Max Range: 4.5228. Min Range: -4.5228

Max Act: 4.3136. Min Act: -0.1700

Data Index: 1475788 (Open Web Text)

Max Activating Token Index: 496

Text #18

Max Range: 4.5228. Min Range: -4.5228

Max Act: 4.2879. Min Act: -0.1700

Data Index: 3949254 (Open Web Text)

Max Activating Token Index: 597

Text #19

Max Range: 4.5228. Min Range: -4.5228

Max Act: 4.3067. Min Act: -0.1700

Data Index: 3988065 (Open Web Text)

Max Activating Token Index: 82