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

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

Neuron 18 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: 0.0295. Min Range: -0.0295

Max Act: 0.0295. Min Act: -0.0006

Data Index: 733914 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0269. Min Act: -0.0006

Data Index: 679913 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0249. Min Act: -0.0006

Data Index: 815566 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0252. Min Act: -0.0006

Data Index: 102291 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0244. Min Act: -0.0006

Data Index: 728198 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0247. Min Act: -0.0006

Data Index: 555352 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0250. Min Act: -0.0006

Data Index: 195679 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0255. Min Act: -0.0006

Data Index: 982215 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0243. Min Act: -0.0006

Data Index: 289397 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0254. Min Act: -0.0006

Data Index: 462462 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0248. Min Act: -0.0006

Data Index: 143754 (C4 (Web Text))

Max Activating Token Index: 935

Text #11

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0246. Min Act: -0.0006

Data Index: 1179629 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0245. Min Act: -0.0006

Data Index: 1184620 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0236. Min Act: -0.0006

Data Index: 357257 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0230. Min Act: -0.0006

Data Index: 1098094 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0245. Min Act: -0.0006

Data Index: 776968 (C4 (Web Text))

Max Activating Token Index: 876

Text #16

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0241. Min Act: -0.0006

Data Index: 83150 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0234. Min Act: -0.0006

Data Index: 610165 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0238. Min Act: -0.0006

Data Index: 1011846 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0236. Min Act: -0.0006

Data Index: 574616 (C4 (Web Text))

Max Activating Token Index: 281