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

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

Neuron 3188 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: 0.0251. Min Range: -0.0251

Max Act: 0.0251. Min Act: -0.0001

Data Index: 1162170 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0198. Min Act: -0.0001

Data Index: 493040 (C4 (Web Text))

Max Activating Token Index: 374

Text #2

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0227. Min Act: -0.0001

Data Index: 784262 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0240. Min Act: -0.0001

Data Index: 850011 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0216. Min Act: -0.0001

Data Index: 781710 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0221. Min Act: -0.0001

Data Index: 486429 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0223. Min Act: -0.0001

Data Index: 1251411 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0206. Min Act: -0.0001

Data Index: 531346 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0208. Min Act: -0.0001

Data Index: 1617034 (Python Code)

Max Activating Token Index: 401

Text #9

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0201. Min Act: -0.0001

Data Index: 718652 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0210. Min Act: -0.0001

Data Index: 649672 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0207. Min Act: -0.0001

Data Index: 820329 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0212. Min Act: -0.0001

Data Index: 329835 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0217. Min Act: -0.0001

Data Index: 948792 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0210. Min Act: -0.0001

Data Index: 371347 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0193. Min Act: -0.0001

Data Index: 252792 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0172. Min Act: -0.0000

Data Index: 754172 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0208. Min Act: -0.0001

Data Index: 24326 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0208. Min Act: -0.0001

Data Index: 9107 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0199. Min Act: -0.0001

Data Index: 759625 (C4 (Web Text))

Max Activating Token Index: 208