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

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

Neuron 891 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: 0.0381. Min Range: -0.0381

Max Act: 0.0381. Min Act: -0.0006

Data Index: 496535 (C4 (Web Text))

Max Activating Token Index: 807

Text #1

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0291. Min Act: -0.0006

Data Index: 1289473 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0262. Min Act: -0.0006

Data Index: 1105127 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0243. Min Act: -0.0006

Data Index: 311492 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0236. Min Act: -0.0006

Data Index: 1240408 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0232. Min Act: -0.0006

Data Index: 758407 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0237. Min Act: -0.0006

Data Index: 1036420 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0232. Min Act: -0.0006

Data Index: 786364 (C4 (Web Text))

Max Activating Token Index: 350

Text #8

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0220. Min Act: -0.0006

Data Index: 729391 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0225. Min Act: -0.0005

Data Index: 492471 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0220. Min Act: -0.0006

Data Index: 765412 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0226. Min Act: -0.0006

Data Index: 1135415 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0220. Min Act: -0.0006

Data Index: 1255524 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0212. Min Act: -0.0006

Data Index: 1106997 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0210. Min Act: -0.0006

Data Index: 1120163 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0201. Min Act: -0.0006

Data Index: 751 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0213. Min Act: -0.0006

Data Index: 1197686 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0206. Min Act: -0.0006

Data Index: 578471 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0201. Min Act: -0.0006

Data Index: 1142303 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0199. Min Act: -0.0006

Data Index: 54175 (C4 (Web Text))

Max Activating Token Index: 689