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

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

Neuron 2033 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: 0.0391. Min Range: -0.0391

Max Act: 0.0391. Min Act: -0.0006

Data Index: 993902 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0383. Min Act: -0.0006

Data Index: 866143 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0381. Min Act: -0.0006

Data Index: 761495 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0365. Min Act: -0.0006

Data Index: 845534 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0360. Min Act: -0.0006

Data Index: 1134365 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0352. Min Act: -0.0006

Data Index: 626064 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0326. Min Act: -0.0006

Data Index: 881139 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0322. Min Act: -0.0006

Data Index: 1156955 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0297. Min Act: -0.0006

Data Index: 619945 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0295. Min Act: -0.0006

Data Index: 547768 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0277. Min Act: -0.0006

Data Index: 1227641 (C4 (Web Text))

Max Activating Token Index: 471

Text #11

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0289. Min Act: -0.0006

Data Index: 40714 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0279. Min Act: -0.0006

Data Index: 1177852 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0285. Min Act: -0.0006

Data Index: 1113404 (C4 (Web Text))

Max Activating Token Index: 275

Text #14

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0277. Min Act: -0.0006

Data Index: 1309606 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0274. Min Act: -0.0006

Data Index: 1017990 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0264. Min Act: -0.0006

Data Index: 141096 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0254. Min Act: -0.0005

Data Index: 953323 (C4 (Web Text))

Max Activating Token Index: 798

Text #18

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0264. Min Act: -0.0006

Data Index: 854958 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0260. Min Act: -0.0006

Data Index: 177929 (C4 (Web Text))

Max Activating Token Index: 440