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

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

Neuron 807 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: 0.0255. Min Range: -0.0255

Max Act: 0.0255. Min Act: -0.0006

Data Index: 59271 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0254. Min Act: -0.0006

Data Index: 708141 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0253. Min Act: -0.0006

Data Index: 897599 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0250. Min Act: -0.0006

Data Index: 428733 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0239. Min Act: -0.0006

Data Index: 613985 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0248. Min Act: -0.0006

Data Index: 684125 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0246. Min Act: -0.0006

Data Index: 1120079 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0248. Min Act: -0.0006

Data Index: 1148324 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0235. Min Act: -0.0006

Data Index: 1139963 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0241. Min Act: -0.0006

Data Index: 833246 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0234. Min Act: -0.0006

Data Index: 204417 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0239. Min Act: -0.0006

Data Index: 650846 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0237. Min Act: -0.0006

Data Index: 962447 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0236. Min Act: -0.0006

Data Index: 982874 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0236. Min Act: -0.0006

Data Index: 1221076 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0231. Min Act: -0.0006

Data Index: 1038838 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0240. Min Act: -0.0006

Data Index: 621332 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0239. Min Act: -0.0006

Data Index: 457503 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0233. Min Act: -0.0006

Data Index: 191389 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0233. Min Act: -0.0006

Data Index: 1110160 (C4 (Web Text))

Max Activating Token Index: 157