Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4642 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0002

Data Index: 943825 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0253. Min Act: -0.0002

Data Index: 1314225 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0259. Min Act: -0.0002

Data Index: 282357 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0249. Min Act: -0.0002

Data Index: 974331 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0247. Min Act: -0.0002

Data Index: 226598 (C4 (Web Text))

Max Activating Token Index: 706

Text #5

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0245. Min Act: -0.0002

Data Index: 210578 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0245. Min Act: -0.0002

Data Index: 920073 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0237. Min Act: -0.0002

Data Index: 1079712 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0238. Min Act: -0.0002

Data Index: 693937 (C4 (Web Text))

Max Activating Token Index: 170

Text #9

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0231. Min Act: -0.0002

Data Index: 484077 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0229. Min Act: -0.0002

Data Index: 167531 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0225. Min Act: -0.0002

Data Index: 55933 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0221. Min Act: -0.0002

Data Index: 1176586 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0226. Min Act: -0.0002

Data Index: 297049 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0224. Min Act: -0.0002

Data Index: 1121161 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0221. Min Act: -0.0002

Data Index: 1131605 (C4 (Web Text))

Max Activating Token Index: 220

Text #16

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0218. Min Act: -0.0003

Data Index: 510484 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0217. Min Act: -0.0002

Data Index: 943133 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0214. Min Act: -0.0002

Data Index: 387770 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0212. Min Act: -0.0002

Data Index: 209615 (C4 (Web Text))

Max Activating Token Index: 375