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

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

Neuron 2015 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: 0.0266. Min Range: -0.0266

Max Act: 0.0259. Min Act: -0.0006

Data Index: 279019 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0264. Min Act: -0.0006

Data Index: 232048 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0258. Min Act: -0.0006

Data Index: 816211 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0266. Min Act: -0.0006

Data Index: 1272177 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0254. Min Act: -0.0006

Data Index: 128258 (C4 (Web Text))

Max Activating Token Index: 792

Text #5

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0255. Min Act: -0.0006

Data Index: 783954 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0254. Min Act: -0.0006

Data Index: 56971 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0254. Min Act: -0.0006

Data Index: 1301568 (C4 (Web Text))

Max Activating Token Index: 1019

Text #8

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0254. Min Act: -0.0006

Data Index: 655064 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0241. Min Act: -0.0006

Data Index: 1299006 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0239. Min Act: -0.0006

Data Index: 1292230 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0249. Min Act: -0.0006

Data Index: 755850 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0251. Min Act: -0.0006

Data Index: 1015462 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0247. Min Act: -0.0006

Data Index: 402758 (C4 (Web Text))

Max Activating Token Index: 504

Text #14

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0263. Min Act: -0.0006

Data Index: 260527 (C4 (Web Text))

Max Activating Token Index: 730

Text #15

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0245. Min Act: -0.0006

Data Index: 1175861 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0239. Min Act: -0.0006

Data Index: 1055502 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0243. Min Act: -0.0006

Data Index: 173017 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0248. Min Act: -0.0006

Data Index: 1043394 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0231. Min Act: -0.0006

Data Index: 281853 (C4 (Web Text))

Max Activating Token Index: 990