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

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

Neuron 1816 in Layer 0

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: 0.0246. Min Act: -0.0006

Data Index: 1352046 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0234. Min Act: -0.0006

Data Index: 685842 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0229. Min Act: -0.0006

Data Index: 334094 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0217. Min Act: -0.0006

Data Index: 829916 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0215. Min Act: -0.0005

Data Index: 1454310 (Python Code)

Max Activating Token Index: 172

Text #5

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0212. Min Act: -0.0006

Data Index: 791091 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0195. Min Act: -0.0006

Data Index: 78971 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0204. Min Act: -0.0006

Data Index: 167921 (C4 (Web Text))

Max Activating Token Index: 574

Text #8

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0198. Min Act: -0.0006

Data Index: 796436 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0201. Min Act: -0.0006

Data Index: 91528 (C4 (Web Text))

Max Activating Token Index: 372

Text #10

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0201. Min Act: -0.0006

Data Index: 536483 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0200. Min Act: -0.0006

Data Index: 442772 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0200. Min Act: -0.0005

Data Index: 1239358 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0194. Min Act: -0.0006

Data Index: 661025 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0193. Min Act: -0.0006

Data Index: 1069031 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0191. Min Act: -0.0006

Data Index: 207069 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0188. Min Act: -0.0006

Data Index: 535665 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0188. Min Act: -0.0006

Data Index: 1398444 (Python Code)

Max Activating Token Index: 595

Text #18

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0186. Min Act: -0.0006

Data Index: 80711 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0186. Min Act: -0.0006

Data Index: 696259 (C4 (Web Text))

Max Activating Token Index: 408