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

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

Neuron 375 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0450. Min Act: -0.0003

Data Index: 213057 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0346. Min Act: -0.0003

Data Index: 670902 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0306. Min Act: -0.0003

Data Index: 243529 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1135102 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0302. Min Act: -0.0003

Data Index: 1294046 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0293. Min Act: -0.0003

Data Index: 506029 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0286. Min Act: -0.0003

Data Index: 1347750 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0281. Min Act: -0.0003

Data Index: 1083385 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0300. Min Act: -0.0003

Data Index: 850587 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0288. Min Act: -0.0002

Data Index: 368097 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0271. Min Act: -0.0003

Data Index: 193630 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0274. Min Act: -0.0003

Data Index: 603784 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0275. Min Act: -0.0003

Data Index: 792579 (C4 (Web Text))

Max Activating Token Index: 588

Text #13

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0263. Min Act: -0.0003

Data Index: 334977 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0268. Min Act: -0.0003

Data Index: 842191 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0271. Min Act: -0.0003

Data Index: 711909 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0265. Min Act: -0.0003

Data Index: 104192 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0268. Min Act: -0.0003

Data Index: 141060 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0268. Min Act: -0.0003

Data Index: 768743 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0260. Min Act: -0.0003

Data Index: 1296258 (C4 (Web Text))

Max Activating Token Index: 940