Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 2005 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0271. Min Act: -0.0006

Data Index: 41199 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0267. Min Act: -0.0006

Data Index: 1016510 (C4 (Web Text))

Max Activating Token Index: 511

Text #2

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0244. Min Act: -0.0006

Data Index: 301825 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0259. Min Act: -0.0006

Data Index: 449836 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0263. Min Act: -0.0006

Data Index: 759165 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0262. Min Act: -0.0006

Data Index: 940426 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0247. Min Act: -0.0006

Data Index: 990342 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0260. Min Act: -0.0006

Data Index: 56315 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0257. Min Act: -0.0006

Data Index: 1096861 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0255. Min Act: -0.0006

Data Index: 772747 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0254. Min Act: -0.0006

Data Index: 198781 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0244. Min Act: -0.0006

Data Index: 1096923 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0254. Min Act: -0.0006

Data Index: 144030 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0253. Min Act: -0.0006

Data Index: 502228 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0251. Min Act: -0.0006

Data Index: 648196 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0250. Min Act: -0.0006

Data Index: 1320859 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0255. Min Act: -0.0006

Data Index: 1204535 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0245. Min Act: -0.0006

Data Index: 451076 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0250. Min Act: -0.0006

Data Index: 883183 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0249. Min Act: -0.0006

Data Index: 843806 (C4 (Web Text))

Max Activating Token Index: 504