Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6038 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5323. Min Range: -0.5323

Max Act: 0.5323. Min Act: -0.0001

Data Index: 959992 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 0.5323. Min Range: -0.5323

Max Act: 0.4973. Min Act: -0.0001

Data Index: 462296 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 0.5323. Min Range: -0.5323

Max Act: 0.5054. Min Act: -0.0000

Data Index: 112900 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 0.5323. Min Range: -0.5323

Max Act: 0.4696. Min Act: -0.0000

Data Index: 420441 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 0.5323. Min Range: -0.5323

Max Act: 0.4509. Min Act: -0.0000

Data Index: 1096292 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 0.5323. Min Range: -0.5323

Max Act: 0.4727. Min Act: -0.0000

Data Index: 516293 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 0.5323. Min Range: -0.5323

Max Act: 0.4523. Min Act: -0.0000

Data Index: 791619 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 0.5323. Min Range: -0.5323

Max Act: 0.4898. Min Act: -0.0000

Data Index: 856980 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 0.5323. Min Range: -0.5323

Max Act: 0.4387. Min Act: -0.0000

Data Index: 539603 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 0.5323. Min Range: -0.5323

Max Act: 0.4719. Min Act: -0.0000

Data Index: 704077 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 0.5323. Min Range: -0.5323

Max Act: 0.4353. Min Act: -0.0000

Data Index: 1056993 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 0.5323. Min Range: -0.5323

Max Act: 0.4620. Min Act: -0.0001

Data Index: 1199394 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 0.5323. Min Range: -0.5323

Max Act: 0.4620. Min Act: -0.0000

Data Index: 1040431 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 0.5323. Min Range: -0.5323

Max Act: 0.4523. Min Act: -0.0000

Data Index: 86917 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 0.5323. Min Range: -0.5323

Max Act: 0.4469. Min Act: -0.0000

Data Index: 206744 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 0.5323. Min Range: -0.5323

Max Act: 0.4190. Min Act: -0.0000

Data Index: 1063626 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 0.5323. Min Range: -0.5323

Max Act: 0.4319. Min Act: -0.0001

Data Index: 460336 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 0.5323. Min Range: -0.5323

Max Act: 0.4427. Min Act: -0.0001

Data Index: 283156 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 0.5323. Min Range: -0.5323

Max Act: 0.4554. Min Act: -0.0000

Data Index: 1011918 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 0.5323. Min Range: -0.5323

Max Act: 0.4293. Min Act: -0.0000

Data Index: 1278988 (C4 (Web Text))

Max Activating Token Index: 62