Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 2013 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.1109. Min Range: -7.1109

Max Act: 7.1109. Min Act: -0.1700

Data Index: 1668093 (Open Web Text)

Max Activating Token Index: 375

Text #1

Max Range: 7.1109. Min Range: -7.1109

Max Act: 7.1109. Min Act: -0.1700

Data Index: 8798642 (Open Web Text)

Max Activating Token Index: 180

Text #2

Max Range: 7.1109. Min Range: -7.1109

Max Act: 7.0484. Min Act: -0.1700

Data Index: 3706944 (Open Web Text)

Max Activating Token Index: 351

Text #3

Max Range: 7.1109. Min Range: -7.1109

Max Act: 7.0484. Min Act: -0.1700

Data Index: 4964709 (Open Web Text)

Max Activating Token Index: 484

Text #4

Max Range: 7.1109. Min Range: -7.1109

Max Act: 7.0172. Min Act: -0.1700

Data Index: 5776507 (Open Web Text)

Max Activating Token Index: 267

Text #5

Max Range: 7.1109. Min Range: -7.1109

Max Act: 6.9859. Min Act: -0.1700

Data Index: 6197548 (Open Web Text)

Max Activating Token Index: 854

Text #6

Max Range: 7.1109. Min Range: -7.1109

Max Act: 6.9547. Min Act: -0.1700

Data Index: 3394022 (Open Web Text)

Max Activating Token Index: 993

Text #7

Max Range: 7.1109. Min Range: -7.1109

Max Act: 6.9859. Min Act: -0.1700

Data Index: 7742595 (Open Web Text)

Max Activating Token Index: 751

Text #8

Max Range: 7.1109. Min Range: -7.1109

Max Act: 6.9547. Min Act: -0.1700

Data Index: 830364 (Open Web Text)

Max Activating Token Index: 422

Text #9

Max Range: 7.1109. Min Range: -7.1109

Max Act: 6.9547. Min Act: -0.1700

Data Index: 5514926 (Open Web Text)

Max Activating Token Index: 882

Text #10

Max Range: 7.1109. Min Range: -7.1109

Max Act: 6.9547. Min Act: -0.1700

Data Index: 477205 (Open Web Text)

Max Activating Token Index: 144

Text #11

Max Range: 7.1109. Min Range: -7.1109

Max Act: 6.9234. Min Act: -0.1700

Data Index: 1766371 (Open Web Text)

Max Activating Token Index: 486

Text #12

Max Range: 7.1109. Min Range: -7.1109

Max Act: 6.9234. Min Act: -0.1700

Data Index: 7025568 (Open Web Text)

Max Activating Token Index: 966

Text #13

Max Range: 7.1109. Min Range: -7.1109

Max Act: 6.9234. Min Act: -0.1700

Data Index: 1761385 (Open Web Text)

Max Activating Token Index: 359

Text #14

Max Range: 7.1109. Min Range: -7.1109

Max Act: 6.9234. Min Act: -0.1700

Data Index: 1449389 (Open Web Text)

Max Activating Token Index: 487

Text #15

Max Range: 7.1109. Min Range: -7.1109

Max Act: 6.9234. Min Act: -0.1700

Data Index: 8462961 (Open Web Text)

Max Activating Token Index: 58

Text #16

Max Range: 7.1109. Min Range: -7.1109

Max Act: 6.9234. Min Act: -0.1700

Data Index: 2927441 (Open Web Text)

Max Activating Token Index: 251

Text #17

Max Range: 7.1109. Min Range: -7.1109

Max Act: 6.8922. Min Act: -0.1700

Data Index: 3176995 (Open Web Text)

Max Activating Token Index: 784

Text #18

Max Range: 7.1109. Min Range: -7.1109

Max Act: 6.8922. Min Act: -0.1700

Data Index: 6531192 (Open Web Text)

Max Activating Token Index: 230

Text #19

Max Range: 7.1109. Min Range: -7.1109

Max Act: 6.8922. Min Act: -0.1700

Data Index: 6326813 (Open Web Text)

Max Activating Token Index: 964