Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 71 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6566. Min Range: -1.6566

Max Act: 1.6396. Min Act: -0.0001

Data Index: 595764 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 1.6566. Min Range: -1.6566

Max Act: 1.6120. Min Act: -0.0001

Data Index: 1183361 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 1.6566. Min Range: -1.6566

Max Act: 1.6566. Min Act: -0.0001

Data Index: 332068 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 1.6566. Min Range: -1.6566

Max Act: 1.5202. Min Act: -0.0001

Data Index: 972695 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 1.6566. Min Range: -1.6566

Max Act: 1.5004. Min Act: -0.0001

Data Index: 854614 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 1.6566. Min Range: -1.6566

Max Act: 1.1754. Min Act: -0.0001

Data Index: 725869 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 1.6566. Min Range: -1.6566

Max Act: 1.3638. Min Act: -0.0001

Data Index: 1205992 (C4 (Web Text))

Max Activating Token Index: 246

Text #7

Max Range: 1.6566. Min Range: -1.6566

Max Act: 1.3096. Min Act: -0.0001

Data Index: 782107 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 1.6566. Min Range: -1.6566

Max Act: 1.3440. Min Act: -0.0001

Data Index: 679871 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 1.6566. Min Range: -1.6566

Max Act: 1.3279. Min Act: -0.0001

Data Index: 294562 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 1.6566. Min Range: -1.6566

Max Act: 1.2873. Min Act: -0.0001

Data Index: 1064441 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 1.6566. Min Range: -1.6566

Max Act: 1.4401. Min Act: -0.0001

Data Index: 514555 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 1.6566. Min Range: -1.6566

Max Act: 1.2573. Min Act: -0.0001

Data Index: 1303195 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 1.6566. Min Range: -1.6566

Max Act: 1.2101. Min Act: -0.0001

Data Index: 623566 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 1.6566. Min Range: -1.6566

Max Act: 1.2382. Min Act: -0.0001

Data Index: 1189082 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 1.6566. Min Range: -1.6566

Max Act: 1.2168. Min Act: -0.0001

Data Index: 574640 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 1.6566. Min Range: -1.6566

Max Act: 1.2134. Min Act: -0.0001

Data Index: 139661 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 1.6566. Min Range: -1.6566

Max Act: 1.2548. Min Act: -0.0001

Data Index: 811415 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 1.6566. Min Range: -1.6566

Max Act: 1.2497. Min Act: -0.0001

Data Index: 1197166 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 1.6566. Min Range: -1.6566

Max Act: 1.1412. Min Act: -0.0001

Data Index: 990087 (C4 (Web Text))

Max Activating Token Index: 672