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

Dataset: Open Web Text

Neuron 433 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: 3.4421. Min Range: -3.4421

Max Act: 3.4421. Min Act: -0.1700

Data Index: 6734396 (Open Web Text)

Max Activating Token Index: 16

Text #1

Max Range: 3.4421. Min Range: -3.4421

Max Act: 3.4072. Min Act: -0.1700

Data Index: 2408945 (Open Web Text)

Max Activating Token Index: 26

Text #2

Max Range: 3.4421. Min Range: -3.4421

Max Act: 3.3981. Min Act: -0.1699

Data Index: 8050187 (Open Web Text)

Max Activating Token Index: 761

Text #3

Max Range: 3.4421. Min Range: -3.4421

Max Act: 3.4038. Min Act: -0.1700

Data Index: 643582 (Open Web Text)

Max Activating Token Index: 40

Text #4

Max Range: 3.4421. Min Range: -3.4421

Max Act: 3.3982. Min Act: -0.1700

Data Index: 5748980 (Open Web Text)

Max Activating Token Index: 86

Text #5

Max Range: 3.4421. Min Range: -3.4421

Max Act: 3.3769. Min Act: -0.1700

Data Index: 5538853 (Open Web Text)

Max Activating Token Index: 18

Text #6

Max Range: 3.4421. Min Range: -3.4421

Max Act: 3.3846. Min Act: -0.1700

Data Index: 4754247 (Open Web Text)

Max Activating Token Index: 392

Text #7

Max Range: 3.4421. Min Range: -3.4421

Max Act: 3.3885. Min Act: -0.1700

Data Index: 7469282 (Open Web Text)

Max Activating Token Index: 388

Text #8

Max Range: 3.4421. Min Range: -3.4421

Max Act: 3.3712. Min Act: -0.1700

Data Index: 4869841 (Open Web Text)

Max Activating Token Index: 452

Text #9

Max Range: 3.4421. Min Range: -3.4421

Max Act: 3.3455. Min Act: -0.1700

Data Index: 1954512 (Open Web Text)

Max Activating Token Index: 1010

Text #10

Max Range: 3.4421. Min Range: -3.4421

Max Act: 3.3483. Min Act: -0.1700

Data Index: 3793072 (Open Web Text)

Max Activating Token Index: 715

Text #11

Max Range: 3.4421. Min Range: -3.4421

Max Act: 3.3460. Min Act: -0.1700

Data Index: 4883705 (Open Web Text)

Max Activating Token Index: 1013

Text #12

Max Range: 3.4421. Min Range: -3.4421

Max Act: 3.3636. Min Act: -0.1700

Data Index: 6745415 (Open Web Text)

Max Activating Token Index: 835

Text #13

Max Range: 3.4421. Min Range: -3.4421

Max Act: 3.3753. Min Act: -0.1700

Data Index: 5833741 (Open Web Text)

Max Activating Token Index: 248

Text #14

Max Range: 3.4421. Min Range: -3.4421

Max Act: 3.3502. Min Act: -0.1700

Data Index: 595254 (Open Web Text)

Max Activating Token Index: 686

Text #15

Max Range: 3.4421. Min Range: -3.4421

Max Act: 3.3746. Min Act: -0.1700

Data Index: 6258134 (Open Web Text)

Max Activating Token Index: 406

Text #16

Max Range: 3.4421. Min Range: -3.4421

Max Act: 3.3802. Min Act: -0.1700

Data Index: 5862915 (Open Web Text)

Max Activating Token Index: 472

Text #17

Max Range: 3.4421. Min Range: -3.4421

Max Act: 3.3650. Min Act: -0.1700

Data Index: 940252 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 3.4421. Min Range: -3.4421

Max Act: 3.3224. Min Act: -0.1700

Data Index: 823907 (Open Web Text)

Max Activating Token Index: 55

Text #19

Max Range: 3.4421. Min Range: -3.4421

Max Act: 3.3188. Min Act: -0.1700

Data Index: 4115945 (Open Web Text)

Max Activating Token Index: 330