Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1826 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0265. Min Act: -0.0006

Data Index: 434138 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0244. Min Act: -0.0006

Data Index: 152994 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0237. Min Act: -0.0006

Data Index: 1203144 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0243. Min Act: -0.0006

Data Index: 62775 (C4 (Web Text))

Max Activating Token Index: 544

Text #4

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0233. Min Act: -0.0006

Data Index: 1072676 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0243. Min Act: -0.0006

Data Index: 596363 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0237. Min Act: -0.0006

Data Index: 618123 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0230. Min Act: -0.0006

Data Index: 1172742 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0231. Min Act: -0.0006

Data Index: 370545 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0231. Min Act: -0.0006

Data Index: 701757 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0229. Min Act: -0.0006

Data Index: 1238821 (C4 (Web Text))

Max Activating Token Index: 310

Text #11

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0234. Min Act: -0.0006

Data Index: 1172936 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0223. Min Act: -0.0006

Data Index: 58914 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0226. Min Act: -0.0006

Data Index: 886419 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0226. Min Act: -0.0006

Data Index: 1349801 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0225. Min Act: -0.0006

Data Index: 744593 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0223. Min Act: -0.0006

Data Index: 18870 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0218. Min Act: -0.0006

Data Index: 1144051 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0222. Min Act: -0.0006

Data Index: 879422 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0222. Min Act: -0.0006

Data Index: 1005247 (C4 (Web Text))

Max Activating Token Index: 515