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

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

Neuron 2968 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: 0.0867. Min Range: -0.0867

Max Act: 0.0867. Min Act: -0.0001

Data Index: 136891 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0383. Min Act: -0.0001

Data Index: 183237 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0352. Min Act: -0.0001

Data Index: 1149430 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0253. Min Act: -0.0001

Data Index: 421098 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0238. Min Act: -0.0001

Data Index: 789920 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0253. Min Act: -0.0001

Data Index: 476473 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0212. Min Act: -0.0001

Data Index: 955477 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0220. Min Act: -0.0001

Data Index: 545913 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0206. Min Act: -0.0001

Data Index: 787319 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0191. Min Act: -0.0001

Data Index: 86290 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0213. Min Act: -0.0001

Data Index: 116669 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0205. Min Act: -0.0001

Data Index: 491346 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0212. Min Act: -0.0001

Data Index: 90956 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0210. Min Act: -0.0001

Data Index: 711135 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0225. Min Act: -0.0001

Data Index: 1192574 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0208. Min Act: -0.0001

Data Index: 126681 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0217. Min Act: -0.0001

Data Index: 1163760 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0212. Min Act: -0.0001

Data Index: 663829 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0204. Min Act: -0.0001

Data Index: 830571 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0195. Min Act: -0.0001

Data Index: 1105066 (C4 (Web Text))

Max Activating Token Index: 305