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

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

Neuron 639 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0296. Min Act: -0.0000

Data Index: 804576 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0272. Min Act: -0.0000

Data Index: 492755 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0269. Min Act: -0.0000

Data Index: 275738 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0304. Min Act: -0.0000

Data Index: 1635865 (Python Code)

Max Activating Token Index: 761

Text #4

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0271. Min Act: -0.0000

Data Index: 779949 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0268. Min Act: -0.0000

Data Index: 223405 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0242. Min Act: -0.0000

Data Index: 725164 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0284. Min Act: -0.0000

Data Index: 1365256 (Python Code)

Max Activating Token Index: 998

Text #8

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0259. Min Act: -0.0000

Data Index: 722854 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0247. Min Act: -0.0000

Data Index: 79036 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0252. Min Act: -0.0000

Data Index: 397496 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0249. Min Act: -0.0000

Data Index: 932021 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0249. Min Act: -0.0000

Data Index: 166420 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0248. Min Act: -0.0000

Data Index: 1053675 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0257. Min Act: -0.0000

Data Index: 42518 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0245. Min Act: -0.0000

Data Index: 799396 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0237. Min Act: -0.0000

Data Index: 558239 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0245. Min Act: -0.0000

Data Index: 981830 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0245. Min Act: -0.0000

Data Index: 882387 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0251. Min Act: -0.0000

Data Index: 131753 (C4 (Web Text))

Max Activating Token Index: 619