Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 570 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0243. Min Act: -0.0006

Data Index: 439145 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0230. Min Act: -0.0006

Data Index: 1320382 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0237. Min Act: -0.0006

Data Index: 755647 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0229. Min Act: -0.0006

Data Index: 751534 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0228. Min Act: -0.0006

Data Index: 87750 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0224. Min Act: -0.0006

Data Index: 414720 (C4 (Web Text))

Max Activating Token Index: 525

Text #6

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0222. Min Act: -0.0006

Data Index: 1317162 (C4 (Web Text))

Max Activating Token Index: 873

Text #7

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0242. Min Act: -0.0006

Data Index: 172836 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0221. Min Act: -0.0006

Data Index: 126166 (C4 (Web Text))

Max Activating Token Index: 160

Text #9

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0210. Min Act: -0.0006

Data Index: 279714 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0219. Min Act: -0.0006

Data Index: 432521 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0219. Min Act: -0.0006

Data Index: 1220027 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0212. Min Act: -0.0006

Data Index: 135925 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0192. Min Act: -0.0006

Data Index: 440077 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0210. Min Act: -0.0006

Data Index: 747496 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0209. Min Act: -0.0006

Data Index: 1065109 (C4 (Web Text))

Max Activating Token Index: 256

Text #16

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0209. Min Act: -0.0006

Data Index: 788907 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0209. Min Act: -0.0006

Data Index: 519432 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0209. Min Act: -0.0006

Data Index: 199354 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0210. Min Act: -0.0006

Data Index: 1223898 (C4 (Web Text))

Max Activating Token Index: 282