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

Dataset: Open Web Text

Neuron 805 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: 2.8967. Min Range: -2.8967

Max Act: 2.8967. Min Act: -0.1700

Data Index: 4514806 (Open Web Text)

Max Activating Token Index: 988

Text #1

Max Range: 2.8967. Min Range: -2.8967

Max Act: 2.8770. Min Act: -0.1700

Data Index: 4506668 (Open Web Text)

Max Activating Token Index: 976

Text #2

Max Range: 2.8967. Min Range: -2.8967

Max Act: 2.8507. Min Act: -0.1700

Data Index: 5577416 (Open Web Text)

Max Activating Token Index: 855

Text #3

Max Range: 2.8967. Min Range: -2.8967

Max Act: 2.8557. Min Act: -0.1700

Data Index: 6221110 (Open Web Text)

Max Activating Token Index: 267

Text #4

Max Range: 2.8967. Min Range: -2.8967

Max Act: 2.8131. Min Act: -0.1700

Data Index: 8414634 (Open Web Text)

Max Activating Token Index: 231

Text #5

Max Range: 2.8967. Min Range: -2.8967

Max Act: 2.8016. Min Act: -0.1700

Data Index: 2611214 (Open Web Text)

Max Activating Token Index: 301

Text #6

Max Range: 2.8967. Min Range: -2.8967

Max Act: 2.8126. Min Act: -0.1700

Data Index: 1717185 (Open Web Text)

Max Activating Token Index: 13

Text #7

Max Range: 2.8967. Min Range: -2.8967

Max Act: 2.8061. Min Act: -0.1700

Data Index: 8569513 (Open Web Text)

Max Activating Token Index: 870

Text #8

Max Range: 2.8967. Min Range: -2.8967

Max Act: 2.8019. Min Act: -0.1700

Data Index: 8614439 (Open Web Text)

Max Activating Token Index: 676

Text #9

Max Range: 2.8967. Min Range: -2.8967

Max Act: 2.7958. Min Act: -0.1700

Data Index: 5183846 (Open Web Text)

Max Activating Token Index: 648

Text #10

Max Range: 2.8967. Min Range: -2.8967

Max Act: 2.7854. Min Act: -0.1700

Data Index: 4716982 (Open Web Text)

Max Activating Token Index: 971

Text #11

Max Range: 2.8967. Min Range: -2.8967

Max Act: 2.7779. Min Act: -0.1700

Data Index: 8345865 (Open Web Text)

Max Activating Token Index: 104

Text #12

Max Range: 2.8967. Min Range: -2.8967

Max Act: 2.7795. Min Act: -0.1700

Data Index: 1042005 (Open Web Text)

Max Activating Token Index: 203

Text #13

Max Range: 2.8967. Min Range: -2.8967

Max Act: 2.7709. Min Act: -0.1700

Data Index: 111273 (Open Web Text)

Max Activating Token Index: 182

Text #14

Max Range: 2.8967. Min Range: -2.8967

Max Act: 2.7765. Min Act: -0.1700

Data Index: 629656 (Open Web Text)

Max Activating Token Index: 553

Text #15

Max Range: 2.8967. Min Range: -2.8967

Max Act: 2.7873. Min Act: -0.1700

Data Index: 784554 (Open Web Text)

Max Activating Token Index: 926

Text #16

Max Range: 2.8967. Min Range: -2.8967

Max Act: 2.7787. Min Act: -0.1700

Data Index: 1373467 (Open Web Text)

Max Activating Token Index: 719

Text #17

Max Range: 2.8967. Min Range: -2.8967

Max Act: 2.7489. Min Act: -0.1700

Data Index: 8139935 (Open Web Text)

Max Activating Token Index: 929

Text #18

Max Range: 2.8967. Min Range: -2.8967

Max Act: 2.7388. Min Act: -0.1700

Data Index: 4750527 (Open Web Text)

Max Activating Token Index: 11

Text #19

Max Range: 2.8967. Min Range: -2.8967

Max Act: 2.7363. Min Act: -0.1700

Data Index: 7536612 (Open Web Text)

Max Activating Token Index: 87