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

Dataset: Open Web Text

Neuron 666 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: 4.4874. Min Range: -4.4874

Max Act: 4.4874. Min Act: -0.1700

Data Index: 6435012 (Open Web Text)

Max Activating Token Index: 962

Text #1

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.4568. Min Act: -0.1700

Data Index: 7887171 (Open Web Text)

Max Activating Token Index: 455

Text #2

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.4474. Min Act: -0.1700

Data Index: 419370 (Open Web Text)

Max Activating Token Index: 854

Text #3

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.4290. Min Act: -0.1700

Data Index: 8197402 (Open Web Text)

Max Activating Token Index: 940

Text #4

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.4069. Min Act: -0.1700

Data Index: 7005038 (Open Web Text)

Max Activating Token Index: 684

Text #5

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.4133. Min Act: -0.1700

Data Index: 8760721 (Open Web Text)

Max Activating Token Index: 70

Text #6

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.4136. Min Act: -0.1700

Data Index: 1969944 (Open Web Text)

Max Activating Token Index: 903

Text #7

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.4168. Min Act: -0.1700

Data Index: 2443419 (Open Web Text)

Max Activating Token Index: 71

Text #8

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.4241. Min Act: -0.1700

Data Index: 8231490 (Open Web Text)

Max Activating Token Index: 437

Text #9

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.3835. Min Act: -0.1700

Data Index: 4376590 (Open Web Text)

Max Activating Token Index: 560

Text #10

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.3917. Min Act: -0.1700

Data Index: 5715578 (Open Web Text)

Max Activating Token Index: 64

Text #11

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.3656. Min Act: -0.1700

Data Index: 99017 (Open Web Text)

Max Activating Token Index: 482

Text #12

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.3708. Min Act: -0.1700

Data Index: 1463400 (Open Web Text)

Max Activating Token Index: 556

Text #13

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.4028. Min Act: -0.1700

Data Index: 1687482 (Open Web Text)

Max Activating Token Index: 584

Text #14

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.4004. Min Act: -0.1700

Data Index: 7743927 (Open Web Text)

Max Activating Token Index: 499

Text #15

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.4072. Min Act: -0.1700

Data Index: 7772668 (Open Web Text)

Max Activating Token Index: 440

Text #16

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.3973. Min Act: -0.1700

Data Index: 4773481 (Open Web Text)

Max Activating Token Index: 52

Text #17

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.3484. Min Act: -0.1700

Data Index: 6997622 (Open Web Text)

Max Activating Token Index: 150

Text #18

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.3589. Min Act: -0.1700

Data Index: 7398531 (Open Web Text)

Max Activating Token Index: 724

Text #19

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.3792. Min Act: -0.1700

Data Index: 1699262 (Open Web Text)

Max Activating Token Index: 964