Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4512 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0423. Min Act: -0.0002

Data Index: 962289 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0361. Min Act: -0.0002

Data Index: 1166004 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0321. Min Act: -0.0002

Data Index: 1325070 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0294. Min Act: -0.0002

Data Index: 265805 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0303. Min Act: -0.0002

Data Index: 992938 (C4 (Web Text))

Max Activating Token Index: 419

Text #5

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0288. Min Act: -0.0002

Data Index: 992080 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0279. Min Act: -0.0002

Data Index: 912077 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0292. Min Act: -0.0002

Data Index: 1214598 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0286. Min Act: -0.0002

Data Index: 973753 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0282. Min Act: -0.0002

Data Index: 1340230 (C4 (Web Text))

Max Activating Token Index: 238

Text #10

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0290. Min Act: -0.0002

Data Index: 1046617 (C4 (Web Text))

Max Activating Token Index: 648

Text #11

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0294. Min Act: -0.0002

Data Index: 538438 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0291. Min Act: -0.0002

Data Index: 232376 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0277. Min Act: -0.0002

Data Index: 899415 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0267. Min Act: -0.0002

Data Index: 977822 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0276. Min Act: -0.0002

Data Index: 1359321 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0276. Min Act: -0.0002

Data Index: 384500 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0280. Min Act: -0.0002

Data Index: 1170240 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0260. Min Act: -0.0002

Data Index: 1388936 (Python Code)

Max Activating Token Index: 4

Text #19

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0274. Min Act: -0.0002

Data Index: 399596 (C4 (Web Text))

Max Activating Token Index: 512