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

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

Neuron 1363 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: 0.0246. Min Range: -0.0246

Max Act: 0.0240. Min Act: -0.0006

Data Index: 777233 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0246. Min Act: -0.0006

Data Index: 1123163 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0231. Min Act: -0.0006

Data Index: 797601 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0229. Min Act: -0.0006

Data Index: 344535 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0236. Min Act: -0.0006

Data Index: 700459 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0237. Min Act: -0.0006

Data Index: 127104 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0231. Min Act: -0.0006

Data Index: 16380 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0240. Min Act: -0.0006

Data Index: 1080713 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0224. Min Act: -0.0006

Data Index: 642555 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0229. Min Act: -0.0006

Data Index: 1104788 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0228. Min Act: -0.0006

Data Index: 860522 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0221. Min Act: -0.0006

Data Index: 1233015 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0223. Min Act: -0.0006

Data Index: 158573 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0223. Min Act: -0.0006

Data Index: 812099 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0219. Min Act: -0.0006

Data Index: 757868 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0222. Min Act: -0.0006

Data Index: 1303508 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0222. Min Act: -0.0006

Data Index: 796041 (C4 (Web Text))

Max Activating Token Index: 637

Text #17

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0212. Min Act: -0.0006

Data Index: 517153 (C4 (Web Text))

Max Activating Token Index: 221

Text #18

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0221. Min Act: -0.0006

Data Index: 318420 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0221. Min Act: -0.0006

Data Index: 609911 (C4 (Web Text))

Max Activating Token Index: 958