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

Dataset: Open Web Text

Neuron 769 in Layer 1

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: 3.1349. Min Range: -3.1349

Max Act: 3.1349. Min Act: -0.1700

Data Index: 4758064 (Open Web Text)

Max Activating Token Index: 30

Text #1

Max Range: 3.1349. Min Range: -3.1349

Max Act: 3.0961. Min Act: -0.1700

Data Index: 4299626 (Open Web Text)

Max Activating Token Index: 438

Text #2

Max Range: 3.1349. Min Range: -3.1349

Max Act: 3.0782. Min Act: -0.1700

Data Index: 2238827 (Open Web Text)

Max Activating Token Index: 421

Text #3

Max Range: 3.1349. Min Range: -3.1349

Max Act: 3.0593. Min Act: -0.1700

Data Index: 3908659 (Open Web Text)

Max Activating Token Index: 82

Text #4

Max Range: 3.1349. Min Range: -3.1349

Max Act: 3.0604. Min Act: -0.1700

Data Index: 7877261 (Open Web Text)

Max Activating Token Index: 976

Text #5

Max Range: 3.1349. Min Range: -3.1349

Max Act: 3.0583. Min Act: -0.1700

Data Index: 4724820 (Open Web Text)

Max Activating Token Index: 576

Text #6

Max Range: 3.1349. Min Range: -3.1349

Max Act: 3.0538. Min Act: -0.1700

Data Index: 7258000 (Open Web Text)

Max Activating Token Index: 74

Text #7

Max Range: 3.1349. Min Range: -3.1349

Max Act: 3.0207. Min Act: -0.1700

Data Index: 647135 (Open Web Text)

Max Activating Token Index: 868

Text #8

Max Range: 3.1349. Min Range: -3.1349

Max Act: 3.0153. Min Act: -0.1700

Data Index: 8004801 (Open Web Text)

Max Activating Token Index: 745

Text #9

Max Range: 3.1349. Min Range: -3.1349

Max Act: 3.0183. Min Act: -0.1700

Data Index: 4361746 (Open Web Text)

Max Activating Token Index: 592

Text #10

Max Range: 3.1349. Min Range: -3.1349

Max Act: 3.0127. Min Act: -0.1700

Data Index: 3710045 (Open Web Text)

Max Activating Token Index: 997

Text #11

Max Range: 3.1349. Min Range: -3.1349

Max Act: 3.0156. Min Act: -0.1700

Data Index: 5933243 (Open Web Text)

Max Activating Token Index: 706

Text #12

Max Range: 3.1349. Min Range: -3.1349

Max Act: 3.0132. Min Act: -0.1700

Data Index: 8637688 (Open Web Text)

Max Activating Token Index: 623

Text #13

Max Range: 3.1349. Min Range: -3.1349

Max Act: 3.0108. Min Act: -0.1700

Data Index: 787190 (Open Web Text)

Max Activating Token Index: 706

Text #14

Max Range: 3.1349. Min Range: -3.1349

Max Act: 2.9859. Min Act: -0.1700

Data Index: 5465296 (Open Web Text)

Max Activating Token Index: 794

Text #15

Max Range: 3.1349. Min Range: -3.1349

Max Act: 2.9850. Min Act: -0.1700

Data Index: 5873293 (Open Web Text)

Max Activating Token Index: 468

Text #16

Max Range: 3.1349. Min Range: -3.1349

Max Act: 2.9875. Min Act: -0.1700

Data Index: 5839013 (Open Web Text)

Max Activating Token Index: 676

Text #17

Max Range: 3.1349. Min Range: -3.1349

Max Act: 2.9859. Min Act: -0.1700

Data Index: 5434947 (Open Web Text)

Max Activating Token Index: 136

Text #18

Max Range: 3.1349. Min Range: -3.1349

Max Act: 2.9695. Min Act: -0.1700

Data Index: 1804753 (Open Web Text)

Max Activating Token Index: 824

Text #19

Max Range: 3.1349. Min Range: -3.1349

Max Act: 2.9635. Min Act: -0.1700

Data Index: 7169150 (Open Web Text)

Max Activating Token Index: 559