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

Dataset: Open Web Text

Neuron 1455 in Layer 2

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: 3.7908. Min Range: -3.7908

Max Act: 3.7908. Min Act: -0.1700

Data Index: 6982939 (Open Web Text)

Max Activating Token Index: 43

Text #1

Max Range: 3.7908. Min Range: -3.7908

Max Act: 3.7518. Min Act: -0.1700

Data Index: 6765969 (Open Web Text)

Max Activating Token Index: 839

Text #2

Max Range: 3.7908. Min Range: -3.7908

Max Act: 3.7572. Min Act: -0.1700

Data Index: 7264464 (Open Web Text)

Max Activating Token Index: 427

Text #3

Max Range: 3.7908. Min Range: -3.7908

Max Act: 3.7273. Min Act: -0.1700

Data Index: 3790535 (Open Web Text)

Max Activating Token Index: 63

Text #4

Max Range: 3.7908. Min Range: -3.7908

Max Act: 3.7224. Min Act: -0.1700

Data Index: 868126 (Open Web Text)

Max Activating Token Index: 364

Text #5

Max Range: 3.7908. Min Range: -3.7908

Max Act: 3.7206. Min Act: -0.1700

Data Index: 89296 (Open Web Text)

Max Activating Token Index: 438

Text #6

Max Range: 3.7908. Min Range: -3.7908

Max Act: 3.6912. Min Act: -0.1700

Data Index: 5627525 (Open Web Text)

Max Activating Token Index: 557

Text #7

Max Range: 3.7908. Min Range: -3.7908

Max Act: 3.6710. Min Act: -0.1700

Data Index: 3633041 (Open Web Text)

Max Activating Token Index: 216

Text #8

Max Range: 3.7908. Min Range: -3.7908

Max Act: 3.6979. Min Act: -0.1700

Data Index: 3046825 (Open Web Text)

Max Activating Token Index: 656

Text #9

Max Range: 3.7908. Min Range: -3.7908

Max Act: 3.6985. Min Act: -0.1700

Data Index: 5247911 (Open Web Text)

Max Activating Token Index: 275

Text #10

Max Range: 3.7908. Min Range: -3.7908

Max Act: 3.6786. Min Act: -0.1700

Data Index: 7417050 (Open Web Text)

Max Activating Token Index: 991

Text #11

Max Range: 3.7908. Min Range: -3.7908

Max Act: 3.6859. Min Act: -0.1700

Data Index: 1307369 (Open Web Text)

Max Activating Token Index: 584

Text #12

Max Range: 3.7908. Min Range: -3.7908

Max Act: 3.6997. Min Act: -0.1700

Data Index: 4649829 (Open Web Text)

Max Activating Token Index: 95

Text #13

Max Range: 3.7908. Min Range: -3.7908

Max Act: 3.7047. Min Act: -0.1700

Data Index: 1147928 (Open Web Text)

Max Activating Token Index: 1005

Text #14

Max Range: 3.7908. Min Range: -3.7908

Max Act: 3.7033. Min Act: -0.1700

Data Index: 6712437 (Open Web Text)

Max Activating Token Index: 381

Text #15

Max Range: 3.7908. Min Range: -3.7908

Max Act: 3.6761. Min Act: -0.1700

Data Index: 6629562 (Open Web Text)

Max Activating Token Index: 938

Text #16

Max Range: 3.7908. Min Range: -3.7908

Max Act: 3.6802. Min Act: -0.1700

Data Index: 6239413 (Open Web Text)

Max Activating Token Index: 718

Text #17

Max Range: 3.7908. Min Range: -3.7908

Max Act: 3.6892. Min Act: -0.1700

Data Index: 5814285 (Open Web Text)

Max Activating Token Index: 267

Text #18

Max Range: 3.7908. Min Range: -3.7908

Max Act: 3.6417. Min Act: -0.1700

Data Index: 5499162 (Open Web Text)

Max Activating Token Index: 715

Text #19

Max Range: 3.7908. Min Range: -3.7908

Max Act: 3.6599. Min Act: -0.1700

Data Index: 5561675 (Open Web Text)

Max Activating Token Index: 844