Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer

Dataset: Open Web Text

Neuron 3570 in Layer 31

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')

Text #0

Max Range: 10.1016. Min Range: -10.1016

Max Act: 10.1016. Min Act: -0.1700

Data Index: 3692062 (Open Web Text)

Max Activating Token Index: 66

Text #1

Max Range: 10.1016. Min Range: -10.1016

Max Act: 10.1016. Min Act: -0.1700

Data Index: 2832635 (Open Web Text)

Max Activating Token Index: 502

Text #2

Max Range: 10.1016. Min Range: -10.1016

Max Act: 10.1016. Min Act: -0.1700

Data Index: 3532036 (Open Web Text)

Max Activating Token Index: 491

Text #3

Max Range: 10.1016. Min Range: -10.1016

Max Act: 10.0391. Min Act: -0.1700

Data Index: 1235349 (Open Web Text)

Max Activating Token Index: 470

Text #4

Max Range: 10.1016. Min Range: -10.1016

Max Act: 9.8516. Min Act: -0.1700

Data Index: 6954737 (Open Web Text)

Max Activating Token Index: 397

Text #5

Max Range: 10.1016. Min Range: -10.1016

Max Act: 9.6641. Min Act: -0.1700

Data Index: 5912352 (Open Web Text)

Max Activating Token Index: 404

Text #6

Max Range: 10.1016. Min Range: -10.1016

Max Act: 9.6641. Min Act: -0.1700

Data Index: 445683 (Open Web Text)

Max Activating Token Index: 327

Text #7

Max Range: 10.1016. Min Range: -10.1016

Max Act: 9.6641. Min Act: -0.1700

Data Index: 4130555 (Open Web Text)

Max Activating Token Index: 176

Text #8

Max Range: 10.1016. Min Range: -10.1016

Max Act: 9.6641. Min Act: -0.1700

Data Index: 1613174 (Open Web Text)

Max Activating Token Index: 493

Text #9

Max Range: 10.1016. Min Range: -10.1016

Max Act: 9.6016. Min Act: -0.1700

Data Index: 1589301 (Open Web Text)

Max Activating Token Index: 52

Text #10

Max Range: 10.1016. Min Range: -10.1016

Max Act: 9.6641. Min Act: -0.1700

Data Index: 3401556 (Open Web Text)

Max Activating Token Index: 394

Text #11

Max Range: 10.1016. Min Range: -10.1016

Max Act: 9.6016. Min Act: -0.1700

Data Index: 4130554 (Open Web Text)

Max Activating Token Index: 359

Text #12

Max Range: 10.1016. Min Range: -10.1016

Max Act: 9.6016. Min Act: -0.1700

Data Index: 6480059 (Open Web Text)

Max Activating Token Index: 262

Text #13

Max Range: 10.1016. Min Range: -10.1016

Max Act: 9.6016. Min Act: -0.1700

Data Index: 8522993 (Open Web Text)

Max Activating Token Index: 618

Text #14

Max Range: 10.1016. Min Range: -10.1016

Max Act: 9.5391. Min Act: -0.1700

Data Index: 6949436 (Open Web Text)

Max Activating Token Index: 811

Text #15

Max Range: 10.1016. Min Range: -10.1016

Max Act: 9.5391. Min Act: -0.1700

Data Index: 6612774 (Open Web Text)

Max Activating Token Index: 587

Text #16

Max Range: 10.1016. Min Range: -10.1016

Max Act: 9.5391. Min Act: -0.1700

Data Index: 6807999 (Open Web Text)

Max Activating Token Index: 566

Text #17

Max Range: 10.1016. Min Range: -10.1016

Max Act: 9.5391. Min Act: -0.1700

Data Index: 343050 (Open Web Text)

Max Activating Token Index: 29

Text #18

Max Range: 10.1016. Min Range: -10.1016

Max Act: 9.5391. Min Act: -0.1700

Data Index: 1232743 (Open Web Text)

Max Activating Token Index: 103

Text #19

Max Range: 10.1016. Min Range: -10.1016

Max Act: 9.5391. Min Act: -0.1700

Data Index: 5824271 (Open Web Text)

Max Activating Token Index: 34