Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1091 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0326. Min Act: -0.0006

Data Index: 745864 (C4 (Web Text))

Max Activating Token Index: 718

Text #1

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0313. Min Act: -0.0006

Data Index: 928785 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0320. Min Act: -0.0006

Data Index: 689882 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0320. Min Act: -0.0006

Data Index: 279010 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0313. Min Act: -0.0006

Data Index: 985080 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0319. Min Act: -0.0006

Data Index: 478858 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0316. Min Act: -0.0006

Data Index: 969955 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0323. Min Act: -0.0006

Data Index: 367821 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0307. Min Act: -0.0006

Data Index: 578821 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0319. Min Act: -0.0006

Data Index: 252463 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0306. Min Act: -0.0006

Data Index: 796827 (C4 (Web Text))

Max Activating Token Index: 643

Text #11

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0317. Min Act: -0.0006

Data Index: 920057 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0300. Min Act: -0.0006

Data Index: 1219318 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0290. Min Act: -0.0006

Data Index: 1064424 (C4 (Web Text))

Max Activating Token Index: 773

Text #14

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0293. Min Act: -0.0006

Data Index: 1619 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0285. Min Act: -0.0006

Data Index: 817928 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0278. Min Act: -0.0006

Data Index: 152338 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0289. Min Act: -0.0006

Data Index: 1308749 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0283. Min Act: -0.0006

Data Index: 143552 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0295. Min Act: -0.0006

Data Index: 222822 (C4 (Web Text))

Max Activating Token Index: 177