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

Dataset: Open Web Text

Neuron 2238 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: 4.9327. Min Range: -4.9327

Max Act: 4.9171. Min Act: -0.1700

Data Index: 6258321 (Open Web Text)

Max Activating Token Index: 494

Text #1

Max Range: 4.9327. Min Range: -4.9327

Max Act: 4.9327. Min Act: -0.1700

Data Index: 8289794 (Open Web Text)

Max Activating Token Index: 99

Text #2

Max Range: 4.9327. Min Range: -4.9327

Max Act: 4.8899. Min Act: -0.1700

Data Index: 2396035 (Open Web Text)

Max Activating Token Index: 567

Text #3

Max Range: 4.9327. Min Range: -4.9327

Max Act: 4.8914. Min Act: -0.1700

Data Index: 7513061 (Open Web Text)

Max Activating Token Index: 367

Text #4

Max Range: 4.9327. Min Range: -4.9327

Max Act: 4.8969. Min Act: -0.1700

Data Index: 7296490 (Open Web Text)

Max Activating Token Index: 696

Text #5

Max Range: 4.9327. Min Range: -4.9327

Max Act: 4.8951. Min Act: -0.1700

Data Index: 1583995 (Open Web Text)

Max Activating Token Index: 980

Text #6

Max Range: 4.9327. Min Range: -4.9327

Max Act: 4.8700. Min Act: -0.1700

Data Index: 6073888 (Open Web Text)

Max Activating Token Index: 746

Text #7

Max Range: 4.9327. Min Range: -4.9327

Max Act: 4.8630. Min Act: -0.1700

Data Index: 1831780 (Open Web Text)

Max Activating Token Index: 506

Text #8

Max Range: 4.9327. Min Range: -4.9327

Max Act: 4.8008. Min Act: -0.1700

Data Index: 1621329 (Open Web Text)

Max Activating Token Index: 429

Text #9

Max Range: 4.9327. Min Range: -4.9327

Max Act: 4.7966. Min Act: -0.1700

Data Index: 5298383 (Open Web Text)

Max Activating Token Index: 529

Text #10

Max Range: 4.9327. Min Range: -4.9327

Max Act: 4.8098. Min Act: -0.1700

Data Index: 6583553 (Open Web Text)

Max Activating Token Index: 40

Text #11

Max Range: 4.9327. Min Range: -4.9327

Max Act: 4.8070. Min Act: -0.1700

Data Index: 4421386 (Open Web Text)

Max Activating Token Index: 825

Text #12

Max Range: 4.9327. Min Range: -4.9327

Max Act: 4.8057. Min Act: -0.1700

Data Index: 7011359 (Open Web Text)

Max Activating Token Index: 89

Text #13

Max Range: 4.9327. Min Range: -4.9327

Max Act: 4.7921. Min Act: -0.1700

Data Index: 7189190 (Open Web Text)

Max Activating Token Index: 498

Text #14

Max Range: 4.9327. Min Range: -4.9327

Max Act: 4.7741. Min Act: -0.1700

Data Index: 95405 (Open Web Text)

Max Activating Token Index: 1005

Text #15

Max Range: 4.9327. Min Range: -4.9327

Max Act: 4.7845. Min Act: -0.1700

Data Index: 5476503 (Open Web Text)

Max Activating Token Index: 1000

Text #16

Max Range: 4.9327. Min Range: -4.9327

Max Act: 4.7585. Min Act: -0.1700

Data Index: 8490404 (Open Web Text)

Max Activating Token Index: 320

Text #17

Max Range: 4.9327. Min Range: -4.9327

Max Act: 4.7219. Min Act: -0.1700

Data Index: 4341508 (Open Web Text)

Max Activating Token Index: 718

Text #18

Max Range: 4.9327. Min Range: -4.9327

Max Act: 4.7290. Min Act: -0.1700

Data Index: 460745 (Open Web Text)

Max Activating Token Index: 737

Text #19

Max Range: 4.9327. Min Range: -4.9327

Max Act: 4.7257. Min Act: -0.1700

Data Index: 4384640 (Open Web Text)

Max Activating Token Index: 658