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

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

Neuron 541 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: 0.0360. Min Range: -0.0360

Max Act: 0.0360. Min Act: -0.0006

Data Index: 599754 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0334. Min Act: -0.0006

Data Index: 396253 (C4 (Web Text))

Max Activating Token Index: 338

Text #2

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0300. Min Act: -0.0006

Data Index: 977237 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0327. Min Act: -0.0006

Data Index: 460111 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0294. Min Act: -0.0006

Data Index: 620432 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0320. Min Act: -0.0006

Data Index: 212991 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0299. Min Act: -0.0006

Data Index: 1225482 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0278. Min Act: -0.0006

Data Index: 488310 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0265. Min Act: -0.0006

Data Index: 108579 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0234. Min Act: -0.0006

Data Index: 406525 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0259. Min Act: -0.0006

Data Index: 806453 (C4 (Web Text))

Max Activating Token Index: 673

Text #11

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0277. Min Act: -0.0006

Data Index: 287495 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0258. Min Act: -0.0006

Data Index: 500824 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0269. Min Act: -0.0006

Data Index: 500911 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0257. Min Act: -0.0006

Data Index: 866436 (C4 (Web Text))

Max Activating Token Index: 949

Text #15

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0273. Min Act: -0.0006

Data Index: 299004 (C4 (Web Text))

Max Activating Token Index: 771

Text #16

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0273. Min Act: -0.0006

Data Index: 133479 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0279. Min Act: -0.0006

Data Index: 633914 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0270. Min Act: -0.0006

Data Index: 113427 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0259. Min Act: -0.0006

Data Index: 21706 (C4 (Web Text))

Max Activating Token Index: 879