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

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

Neuron 2877 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0283. Min Act: -0.0001

Data Index: 334789 (C4 (Web Text))

Max Activating Token Index: 154

Text #1

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0280. Min Act: -0.0001

Data Index: 954855 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0280. Min Act: -0.0001

Data Index: 446764 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0225. Min Act: -0.0001

Data Index: 1149073 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0260. Min Act: -0.0001

Data Index: 597621 (C4 (Web Text))

Max Activating Token Index: 209

Text #5

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0277. Min Act: -0.0001

Data Index: 689369 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0243. Min Act: -0.0001

Data Index: 909414 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0227. Min Act: -0.0001

Data Index: 1014409 (C4 (Web Text))

Max Activating Token Index: 183

Text #8

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0223. Min Act: -0.0001

Data Index: 278806 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0232. Min Act: -0.0001

Data Index: 1249364 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0220. Min Act: -0.0001

Data Index: 800061 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0224. Min Act: -0.0001

Data Index: 46044 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0229. Min Act: -0.0001

Data Index: 807229 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0246. Min Act: -0.0000

Data Index: 932591 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0218. Min Act: -0.0001

Data Index: 834333 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0208. Min Act: -0.0001

Data Index: 105435 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0208. Min Act: -0.0001

Data Index: 984374 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0213. Min Act: -0.0001

Data Index: 1512779 (Python Code)

Max Activating Token Index: 129

Text #18

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0199. Min Act: -0.0001

Data Index: 170486 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0201. Min Act: -0.0001

Data Index: 1600354 (Python Code)

Max Activating Token Index: 194