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

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

Neuron 1938 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: 0.0248. Min Range: -0.0248

Max Act: 0.0248. Min Act: -0.0006

Data Index: 1267315 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0211. Min Act: -0.0006

Data Index: 681549 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0202. Min Act: -0.0006

Data Index: 726312 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0189. Min Act: -0.0006

Data Index: 584860 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0191. Min Act: -0.0006

Data Index: 1092912 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0200. Min Act: -0.0006

Data Index: 399758 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0191. Min Act: -0.0006

Data Index: 1413669 (Python Code)

Max Activating Token Index: 544

Text #7

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0195. Min Act: -0.0006

Data Index: 309828 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0205. Min Act: -0.0006

Data Index: 1073373 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0186. Min Act: -0.0006

Data Index: 1289025 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0182. Min Act: -0.0006

Data Index: 1417717 (Python Code)

Max Activating Token Index: 728

Text #11

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0186. Min Act: -0.0006

Data Index: 617424 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0176. Min Act: -0.0006

Data Index: 767530 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0184. Min Act: -0.0006

Data Index: 1529863 (Python Code)

Max Activating Token Index: 161

Text #14

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0182. Min Act: -0.0006

Data Index: 833057 (C4 (Web Text))

Max Activating Token Index: 872

Text #15

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0185. Min Act: -0.0006

Data Index: 1298658 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0177. Min Act: -0.0006

Data Index: 307558 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0181. Min Act: -0.0006

Data Index: 159338 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0183. Min Act: -0.0006

Data Index: 347658 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0177. Min Act: -0.0006

Data Index: 800196 (C4 (Web Text))

Max Activating Token Index: 904