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

Dataset: Open Web Text

Neuron 452 in Layer 4

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: 3.4984. Min Range: -3.4984

Max Act: 3.4984. Min Act: -0.1700

Data Index: 3304539 (Open Web Text)

Max Activating Token Index: 920

Text #1

Max Range: 3.4984. Min Range: -3.4984

Max Act: 3.4455. Min Act: -0.1700

Data Index: 8030443 (Open Web Text)

Max Activating Token Index: 341

Text #2

Max Range: 3.4984. Min Range: -3.4984

Max Act: 3.4133. Min Act: -0.1700

Data Index: 7915497 (Open Web Text)

Max Activating Token Index: 177

Text #3

Max Range: 3.4984. Min Range: -3.4984

Max Act: 3.4181. Min Act: -0.1700

Data Index: 4313872 (Open Web Text)

Max Activating Token Index: 682

Text #4

Max Range: 3.4984. Min Range: -3.4984

Max Act: 3.3894. Min Act: -0.1700

Data Index: 2070004 (Open Web Text)

Max Activating Token Index: 58

Text #5

Max Range: 3.4984. Min Range: -3.4984

Max Act: 3.3983. Min Act: -0.1700

Data Index: 4984631 (Open Web Text)

Max Activating Token Index: 968

Text #6

Max Range: 3.4984. Min Range: -3.4984

Max Act: 3.3895. Min Act: -0.1700

Data Index: 8369980 (Open Web Text)

Max Activating Token Index: 321

Text #7

Max Range: 3.4984. Min Range: -3.4984

Max Act: 3.3639. Min Act: -0.1700

Data Index: 8575892 (Open Web Text)

Max Activating Token Index: 976

Text #8

Max Range: 3.4984. Min Range: -3.4984

Max Act: 3.4021. Min Act: -0.1700

Data Index: 8330196 (Open Web Text)

Max Activating Token Index: 533

Text #9

Max Range: 3.4984. Min Range: -3.4984

Max Act: 3.3537. Min Act: -0.1700

Data Index: 3218905 (Open Web Text)

Max Activating Token Index: 51

Text #10

Max Range: 3.4984. Min Range: -3.4984

Max Act: 3.3610. Min Act: -0.1700

Data Index: 8698496 (Open Web Text)

Max Activating Token Index: 473

Text #11

Max Range: 3.4984. Min Range: -3.4984

Max Act: 3.3385. Min Act: -0.1700

Data Index: 887223 (Open Web Text)

Max Activating Token Index: 348

Text #12

Max Range: 3.4984. Min Range: -3.4984

Max Act: 3.3371. Min Act: -0.1700

Data Index: 588957 (Open Web Text)

Max Activating Token Index: 338

Text #13

Max Range: 3.4984. Min Range: -3.4984

Max Act: 3.3297. Min Act: -0.1700

Data Index: 5518955 (Open Web Text)

Max Activating Token Index: 339

Text #14

Max Range: 3.4984. Min Range: -3.4984

Max Act: 3.2685. Min Act: -0.1700

Data Index: 1988781 (Open Web Text)

Max Activating Token Index: 268

Text #15

Max Range: 3.4984. Min Range: -3.4984

Max Act: 3.2599. Min Act: -0.1700

Data Index: 8111803 (Open Web Text)

Max Activating Token Index: 248

Text #16

Max Range: 3.4984. Min Range: -3.4984

Max Act: 3.2752. Min Act: -0.1700

Data Index: 75064 (Open Web Text)

Max Activating Token Index: 754

Text #17

Max Range: 3.4984. Min Range: -3.4984

Max Act: 3.2397. Min Act: -0.1700

Data Index: 6136656 (Open Web Text)

Max Activating Token Index: 341

Text #18

Max Range: 3.4984. Min Range: -3.4984

Max Act: 3.2331. Min Act: -0.1700

Data Index: 7966439 (Open Web Text)

Max Activating Token Index: 248

Text #19

Max Range: 3.4984. Min Range: -3.4984

Max Act: 3.2025. Min Act: -0.1700

Data Index: 2727669 (Open Web Text)

Max Activating Token Index: 365