Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4715 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.7227. Min Act: -0.0000

Data Index: 1064512 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.6955. Min Act: -0.0000

Data Index: 877495 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.5920. Min Act: -0.0000

Data Index: 1032740 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.5690. Min Act: -0.0000

Data Index: 325640 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.5196. Min Act: -0.0000

Data Index: 262239 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.5177. Min Act: 0.0000

Data Index: 476914 (C4 (Web Text))

Max Activating Token Index: 499

Text #6

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.4705. Min Act: -0.0000

Data Index: 398021 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.4105. Min Act: -0.0000

Data Index: 109525 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.4401. Min Act: -0.0000

Data Index: 672664 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.4376. Min Act: -0.0000

Data Index: 934166 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.4182. Min Act: -0.0000

Data Index: 897992 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.4515. Min Act: -0.0000

Data Index: 538260 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.4258. Min Act: -0.0000

Data Index: 688946 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.4185. Min Act: 0.0000

Data Index: 119119 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.4182. Min Act: -0.0000

Data Index: 512842 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.4309. Min Act: -0.0000

Data Index: 113369 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.4135. Min Act: 0.0000

Data Index: 260901 (C4 (Web Text))

Max Activating Token Index: 191

Text #17

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.4077. Min Act: -0.0000

Data Index: 877256 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.4165. Min Act: -0.0000

Data Index: 1235733 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.3984. Min Act: -0.0000

Data Index: 996083 (C4 (Web Text))

Max Activating Token Index: 55