Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 163 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0681. Min Act: -0.0002

Data Index: 1229125 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0461. Min Act: -0.0002

Data Index: 1251230 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0394. Min Act: -0.0002

Data Index: 1349294 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0389. Min Act: -0.0002

Data Index: 578321 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0391. Min Act: -0.0002

Data Index: 843175 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0376. Min Act: -0.0002

Data Index: 703447 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0366. Min Act: -0.0002

Data Index: 478295 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0367. Min Act: -0.0002

Data Index: 1109222 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0378. Min Act: -0.0002

Data Index: 208731 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0361. Min Act: -0.0002

Data Index: 854662 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0347. Min Act: -0.0002

Data Index: 1220169 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0326. Min Act: -0.0002

Data Index: 1224140 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0344. Min Act: -0.0002

Data Index: 168384 (C4 (Web Text))

Max Activating Token Index: 558

Text #13

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0363. Min Act: -0.0002

Data Index: 1043480 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0333. Min Act: -0.0002

Data Index: 677780 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0359. Min Act: -0.0002

Data Index: 838799 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0328. Min Act: -0.0002

Data Index: 53839 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0335. Min Act: -0.0002

Data Index: 1072308 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0346. Min Act: -0.0002

Data Index: 1254150 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0330. Min Act: -0.0002

Data Index: 1045566 (C4 (Web Text))

Max Activating Token Index: 563