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

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

Neuron 840 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: 0.0324. Min Range: -0.0324

Max Act: 0.0324. Min Act: -0.0006

Data Index: 998623 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0283. Min Act: -0.0006

Data Index: 322347 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0286. Min Act: -0.0006

Data Index: 214230 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0290. Min Act: -0.0006

Data Index: 153562 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0277. Min Act: -0.0006

Data Index: 953341 (C4 (Web Text))

Max Activating Token Index: 375

Text #5

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0277. Min Act: -0.0006

Data Index: 502903 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0278. Min Act: -0.0006

Data Index: 722234 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0269. Min Act: -0.0006

Data Index: 955478 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0254. Min Act: -0.0006

Data Index: 824005 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0253. Min Act: -0.0006

Data Index: 195211 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0270. Min Act: -0.0006

Data Index: 1190457 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0247. Min Act: -0.0006

Data Index: 938758 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0249. Min Act: -0.0006

Data Index: 1001969 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0260. Min Act: -0.0006

Data Index: 149676 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0242. Min Act: -0.0006

Data Index: 1269693 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0255. Min Act: -0.0006

Data Index: 365060 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0255. Min Act: -0.0006

Data Index: 1087797 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0249. Min Act: -0.0006

Data Index: 486007 (C4 (Web Text))

Max Activating Token Index: 388

Text #18

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0247. Min Act: -0.0006

Data Index: 67473 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0255. Min Act: -0.0006

Data Index: 312308 (C4 (Web Text))

Max Activating Token Index: 740