Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2366 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0271. Min Act: -0.0004

Data Index: 1174907 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0230. Min Act: -0.0004

Data Index: 761532 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0248. Min Act: -0.0004

Data Index: 1609717 (Python Code)

Max Activating Token Index: 75

Text #3

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0235. Min Act: -0.0004

Data Index: 408028 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0237. Min Act: -0.0004

Data Index: 390417 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0221. Min Act: -0.0004

Data Index: 900418 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0229. Min Act: -0.0004

Data Index: 385534 (C4 (Web Text))

Max Activating Token Index: 980

Text #7

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0228. Min Act: -0.0004

Data Index: 530959 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0232. Min Act: -0.0004

Data Index: 459519 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0227. Min Act: -0.0004

Data Index: 1622294 (Python Code)

Max Activating Token Index: 879

Text #10

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0230. Min Act: -0.0004

Data Index: 602071 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0193. Min Act: -0.0004

Data Index: 1350497 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0211. Min Act: -0.0004

Data Index: 753921 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0220. Min Act: -0.0004

Data Index: 590198 (C4 (Web Text))

Max Activating Token Index: 922

Text #14

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0214. Min Act: -0.0004

Data Index: 1273753 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0237. Min Act: -0.0004

Data Index: 1398358 (Python Code)

Max Activating Token Index: 204

Text #16

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0218. Min Act: -0.0004

Data Index: 155935 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0180. Min Act: -0.0004

Data Index: 823527 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0210. Min Act: -0.0004

Data Index: 757141 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0223. Min Act: -0.0004

Data Index: 480013 (C4 (Web Text))

Max Activating Token Index: 799