Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1978 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0225. Min Act: -0.0006

Data Index: 978279 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0209. Min Act: -0.0006

Data Index: 404453 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0194. Min Act: -0.0005

Data Index: 1050152 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0192. Min Act: -0.0006

Data Index: 161014 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0191. Min Act: -0.0006

Data Index: 584445 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0190. Min Act: -0.0006

Data Index: 1482160 (Python Code)

Max Activating Token Index: 13

Text #6

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0188. Min Act: -0.0006

Data Index: 96590 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0191. Min Act: -0.0006

Data Index: 596385 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0186. Min Act: -0.0006

Data Index: 88862 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0184. Min Act: -0.0005

Data Index: 142435 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0180. Min Act: -0.0006

Data Index: 824500 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0182. Min Act: -0.0006

Data Index: 105378 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0177. Min Act: -0.0005

Data Index: 106951 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0182. Min Act: -0.0006

Data Index: 456350 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0177. Min Act: -0.0005

Data Index: 67895 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0181. Min Act: -0.0006

Data Index: 1317500 (C4 (Web Text))

Max Activating Token Index: 288

Text #16

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0180. Min Act: -0.0006

Data Index: 236855 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0180. Min Act: -0.0006

Data Index: 886140 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0180. Min Act: -0.0006

Data Index: 795290 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0175. Min Act: -0.0006

Data Index: 842632 (C4 (Web Text))

Max Activating Token Index: 193