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

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

Neuron 4203 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2282. Min Range: -1.2282

Max Act: 1.2282. Min Act: -0.0000

Data Index: 893348 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 1.2282. Min Range: -1.2282

Max Act: 1.0555. Min Act: -0.0000

Data Index: 219476 (C4 (Web Text))

Max Activating Token Index: 485

Text #2

Max Range: 1.2282. Min Range: -1.2282

Max Act: 0.9792. Min Act: -0.0000

Data Index: 885285 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 1.2282. Min Range: -1.2282

Max Act: 0.9448. Min Act: -0.0000

Data Index: 1133738 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 1.2282. Min Range: -1.2282

Max Act: 0.9912. Min Act: -0.0000

Data Index: 849993 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 1.2282. Min Range: -1.2282

Max Act: 0.8202. Min Act: -0.0000

Data Index: 99947 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 1.2282. Min Range: -1.2282

Max Act: 0.8408. Min Act: -0.0000

Data Index: 913383 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 1.2282. Min Range: -1.2282

Max Act: 0.8596. Min Act: -0.0000

Data Index: 340946 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 1.2282. Min Range: -1.2282

Max Act: 0.8558. Min Act: -0.0000

Data Index: 104344 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 1.2282. Min Range: -1.2282

Max Act: 0.8252. Min Act: -0.0000

Data Index: 702179 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 1.2282. Min Range: -1.2282

Max Act: 0.8828. Min Act: -0.0000

Data Index: 312519 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 1.2282. Min Range: -1.2282

Max Act: 0.7990. Min Act: -0.0000

Data Index: 601667 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 1.2282. Min Range: -1.2282

Max Act: 0.8461. Min Act: -0.0000

Data Index: 888864 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 1.2282. Min Range: -1.2282

Max Act: 0.7166. Min Act: -0.0000

Data Index: 889505 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 1.2282. Min Range: -1.2282

Max Act: 0.7751. Min Act: -0.0000

Data Index: 849997 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 1.2282. Min Range: -1.2282

Max Act: 0.7467. Min Act: -0.0000

Data Index: 840895 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 1.2282. Min Range: -1.2282

Max Act: 0.7598. Min Act: -0.0000

Data Index: 729373 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 1.2282. Min Range: -1.2282

Max Act: 0.8241. Min Act: -0.0000

Data Index: 265199 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 1.2282. Min Range: -1.2282

Max Act: 0.8671. Min Act: -0.0000

Data Index: 678802 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 1.2282. Min Range: -1.2282

Max Act: 0.8193. Min Act: -0.0000

Data Index: 1019486 (C4 (Web Text))

Max Activating Token Index: 719