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

Dataset: Open Web Text

Neuron 712 in Layer 0

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: 4.0730. Min Range: -4.0730

Max Act: 4.0730. Min Act: -0.1700

Data Index: 4595026 (Open Web Text)

Max Activating Token Index: 634

Text #1

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.9534. Min Act: -0.1700

Data Index: 8303523 (Open Web Text)

Max Activating Token Index: 782

Text #2

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.9077. Min Act: -0.1700

Data Index: 133533 (Open Web Text)

Max Activating Token Index: 579

Text #3

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.9183. Min Act: -0.1700

Data Index: 5092726 (Open Web Text)

Max Activating Token Index: 231

Text #4

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.9010. Min Act: -0.1700

Data Index: 1185412 (Open Web Text)

Max Activating Token Index: 870

Text #5

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.8778. Min Act: -0.1700

Data Index: 7778960 (Open Web Text)

Max Activating Token Index: 158

Text #6

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.8552. Min Act: -0.1700

Data Index: 4551995 (Open Web Text)

Max Activating Token Index: 272

Text #7

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.8400. Min Act: -0.1700

Data Index: 224308 (Open Web Text)

Max Activating Token Index: 77

Text #8

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.8544. Min Act: -0.1700

Data Index: 5846767 (Open Web Text)

Max Activating Token Index: 699

Text #9

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.8462. Min Act: -0.1700

Data Index: 2155264 (Open Web Text)

Max Activating Token Index: 369

Text #10

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.8299. Min Act: -0.1700

Data Index: 1931410 (Open Web Text)

Max Activating Token Index: 636

Text #11

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.8355. Min Act: -0.1700

Data Index: 8321150 (Open Web Text)

Max Activating Token Index: 232

Text #12

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.8352. Min Act: -0.1700

Data Index: 1112247 (Open Web Text)

Max Activating Token Index: 466

Text #13

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.8273. Min Act: -0.1700

Data Index: 8794514 (Open Web Text)

Max Activating Token Index: 700

Text #14

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.8412. Min Act: -0.1700

Data Index: 2149200 (Open Web Text)

Max Activating Token Index: 622

Text #15

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.8332. Min Act: -0.1700

Data Index: 5136647 (Open Web Text)

Max Activating Token Index: 748

Text #16

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.8333. Min Act: -0.1700

Data Index: 1560314 (Open Web Text)

Max Activating Token Index: 563

Text #17

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.8371. Min Act: -0.1700

Data Index: 5333949 (Open Web Text)

Max Activating Token Index: 407

Text #18

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.7970. Min Act: -0.1700

Data Index: 4920598 (Open Web Text)

Max Activating Token Index: 586

Text #19

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.7981. Min Act: -0.1700

Data Index: 4924482 (Open Web Text)

Max Activating Token Index: 959