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

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

Neuron 540 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0002

Data Index: 620849 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0256. Min Act: -0.0002

Data Index: 27992 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0257. Min Act: -0.0002

Data Index: 342586 (C4 (Web Text))

Max Activating Token Index: 106

Text #3

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0259. Min Act: -0.0002

Data Index: 882131 (C4 (Web Text))

Max Activating Token Index: 529

Text #4

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0283. Min Act: -0.0002

Data Index: 912863 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0223. Min Act: -0.0002

Data Index: 176667 (C4 (Web Text))

Max Activating Token Index: 895

Text #6

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0228. Min Act: -0.0002

Data Index: 601045 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0247. Min Act: -0.0002

Data Index: 523692 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0250. Min Act: -0.0002

Data Index: 384682 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0221. Min Act: -0.0002

Data Index: 1143520 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0220. Min Act: -0.0002

Data Index: 650032 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0240. Min Act: -0.0002

Data Index: 794885 (C4 (Web Text))

Max Activating Token Index: 176

Text #12

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0257. Min Act: -0.0002

Data Index: 71349 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0232. Min Act: -0.0002

Data Index: 944351 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0244. Min Act: -0.0002

Data Index: 596320 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0240. Min Act: -0.0002

Data Index: 437216 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0244. Min Act: -0.0002

Data Index: 662041 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1042280 (C4 (Web Text))

Max Activating Token Index: 927

Text #18

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0226. Min Act: -0.0002

Data Index: 202843 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0226. Min Act: -0.0002

Data Index: 1140109 (C4 (Web Text))

Max Activating Token Index: 830