Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3200 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0253. Min Act: -0.0002

Data Index: 754412 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0246. Min Act: -0.0002

Data Index: 1323952 (C4 (Web Text))

Max Activating Token Index: 225

Text #2

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0240. Min Act: -0.0002

Data Index: 1007322 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0243. Min Act: -0.0002

Data Index: 695147 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0240. Min Act: -0.0002

Data Index: 874510 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0239. Min Act: -0.0002

Data Index: 960522 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0237. Min Act: -0.0002

Data Index: 1285239 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0227. Min Act: -0.0002

Data Index: 1074519 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0225. Min Act: -0.0002

Data Index: 428037 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1041518 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0224. Min Act: -0.0002

Data Index: 702855 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0223. Min Act: -0.0002

Data Index: 423757 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0218. Min Act: -0.0002

Data Index: 659284 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0218. Min Act: -0.0002

Data Index: 697905 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0220. Min Act: -0.0002

Data Index: 1140090 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0219. Min Act: -0.0002

Data Index: 212999 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0213. Min Act: -0.0002

Data Index: 1257500 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0216. Min Act: -0.0002

Data Index: 651565 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0211. Min Act: -0.0002

Data Index: 1039514 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0211. Min Act: -0.0002

Data Index: 145813 (C4 (Web Text))

Max Activating Token Index: 210