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

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

Neuron 1856 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: 0.0272. Min Range: -0.0272

Max Act: 0.0272. Min Act: -0.0006

Data Index: 222490 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0270. Min Act: -0.0006

Data Index: 470172 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0257. Min Act: -0.0006

Data Index: 1075708 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0255. Min Act: -0.0006

Data Index: 1324103 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0247. Min Act: -0.0006

Data Index: 1185542 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0245. Min Act: -0.0006

Data Index: 246210 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0241. Min Act: -0.0006

Data Index: 96196 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0237. Min Act: -0.0006

Data Index: 227364 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0244. Min Act: -0.0006

Data Index: 147120 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0238. Min Act: -0.0006

Data Index: 244802 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0232. Min Act: -0.0006

Data Index: 1007370 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0232. Min Act: -0.0006

Data Index: 27502 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0233. Min Act: -0.0006

Data Index: 1352688 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0227. Min Act: -0.0006

Data Index: 215476 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0226. Min Act: -0.0006

Data Index: 1201628 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0229. Min Act: -0.0006

Data Index: 969527 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0221. Min Act: -0.0006

Data Index: 66084 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0212. Min Act: -0.0006

Data Index: 451233 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0221. Min Act: -0.0006

Data Index: 1312364 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0215. Min Act: -0.0006

Data Index: 1040511 (C4 (Web Text))

Max Activating Token Index: 356