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

Dataset: Open Web Text

Neuron 195 in Layer 18

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1109. Min Range: -5.1109

Max Act: 5.1109. Min Act: -0.1700

Data Index: 740150 (Open Web Text)

Max Activating Token Index: 794

Text #1

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.8921. Min Act: -0.1700

Data Index: 1734317 (Open Web Text)

Max Activating Token Index: 74

Text #2

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.8921. Min Act: -0.1700

Data Index: 7029257 (Open Web Text)

Max Activating Token Index: 617

Text #3

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.6421. Min Act: -0.1700

Data Index: 4720796 (Open Web Text)

Max Activating Token Index: 432

Text #4

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.6421. Min Act: -0.1700

Data Index: 3439288 (Open Web Text)

Max Activating Token Index: 272

Text #5

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.6734. Min Act: -0.1700

Data Index: 7154046 (Open Web Text)

Max Activating Token Index: 931

Text #6

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.6421. Min Act: -0.1700

Data Index: 4211729 (Open Web Text)

Max Activating Token Index: 344

Text #7

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.6421. Min Act: -0.1700

Data Index: 6082781 (Open Web Text)

Max Activating Token Index: 852

Text #8

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.6109. Min Act: -0.1700

Data Index: 3530472 (Open Web Text)

Max Activating Token Index: 293

Text #9

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.6109. Min Act: -0.1700

Data Index: 2930402 (Open Web Text)

Max Activating Token Index: 421

Text #10

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.5796. Min Act: -0.1700

Data Index: 3893730 (Open Web Text)

Max Activating Token Index: 836

Text #11

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.5171. Min Act: -0.1700

Data Index: 2334190 (Open Web Text)

Max Activating Token Index: 863

Text #12

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.5171. Min Act: -0.1700

Data Index: 2230250 (Open Web Text)

Max Activating Token Index: 418

Text #13

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.5171. Min Act: -0.1700

Data Index: 2018165 (Open Web Text)

Max Activating Token Index: 439

Text #14

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.4859. Min Act: -0.1700

Data Index: 5247188 (Open Web Text)

Max Activating Token Index: 321

Text #15

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.4234. Min Act: -0.1700

Data Index: 4088699 (Open Web Text)

Max Activating Token Index: 253

Text #16

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.4234. Min Act: -0.1700

Data Index: 2636012 (Open Web Text)

Max Activating Token Index: 364

Text #17

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.4234. Min Act: -0.1700

Data Index: 1012627 (Open Web Text)

Max Activating Token Index: 960

Text #18

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.3921. Min Act: -0.1700

Data Index: 2051146 (Open Web Text)

Max Activating Token Index: 665

Text #19

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.3921. Min Act: -0.1700

Data Index: 6864961 (Open Web Text)

Max Activating Token Index: 63