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

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

Neuron 758 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: 0.0344. Min Range: -0.0344

Max Act: 0.0344. Min Act: -0.0006

Data Index: 826874 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0319. Min Act: -0.0006

Data Index: 44804 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0315. Min Act: -0.0006

Data Index: 793924 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0291. Min Act: -0.0006

Data Index: 888787 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0287. Min Act: -0.0006

Data Index: 429117 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0280. Min Act: -0.0006

Data Index: 514821 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0278. Min Act: -0.0006

Data Index: 1030219 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0276. Min Act: -0.0005

Data Index: 40428 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0255. Min Act: -0.0005

Data Index: 1022210 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0247. Min Act: -0.0006

Data Index: 1137196 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0233. Min Act: -0.0006

Data Index: 986911 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0225. Min Act: -0.0005

Data Index: 464063 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0216. Min Act: -0.0006

Data Index: 358078 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0214. Min Act: -0.0005

Data Index: 796647 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0213. Min Act: -0.0006

Data Index: 816156 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0210. Min Act: -0.0006

Data Index: 630513 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0208. Min Act: -0.0006

Data Index: 535309 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0202. Min Act: -0.0006

Data Index: 804565 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0210. Min Act: -0.0005

Data Index: 29195 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0209. Min Act: -0.0006

Data Index: 1031009 (C4 (Web Text))

Max Activating Token Index: 983