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

Dataset: The Pile

Neuron 2667 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.7735. Min Act: -0.0000

Data Index: 576307 (The Pile)

Max Activating Token Index: 756

Text #1

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.5035. Min Act: -0.0000

Data Index: 1988732 (The Pile)

Max Activating Token Index: 9

Text #2

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.4980. Min Act: -0.0000

Data Index: 1240337 (The Pile)

Max Activating Token Index: 205

Text #3

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.4722. Min Act: -0.0000

Data Index: 224536 (The Pile)

Max Activating Token Index: 20

Text #4

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.4854. Min Act: -0.0000

Data Index: 619353 (The Pile)

Max Activating Token Index: 23

Text #5

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.4836. Min Act: -0.0000

Data Index: 1546291 (The Pile)

Max Activating Token Index: 14

Text #6

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.4549. Min Act: -0.0000

Data Index: 425422 (The Pile)

Max Activating Token Index: 162

Text #7

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.4565. Min Act: -0.0000

Data Index: 599625 (The Pile)

Max Activating Token Index: 73

Text #8

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.4545. Min Act: -0.0000

Data Index: 279359 (The Pile)

Max Activating Token Index: 6

Text #9

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.4395. Min Act: -0.0000

Data Index: 1799504 (The Pile)

Max Activating Token Index: 271

Text #10

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.4625. Min Act: -0.0000

Data Index: 353659 (The Pile)

Max Activating Token Index: 387

Text #11

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.4583. Min Act: -0.0000

Data Index: 1110309 (The Pile)

Max Activating Token Index: 18

Text #12

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.4298. Min Act: -0.0000

Data Index: 185818 (The Pile)

Max Activating Token Index: 163

Text #13

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.4616. Min Act: -0.0000

Data Index: 1921294 (The Pile)

Max Activating Token Index: 46

Text #14

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.4359. Min Act: -0.0000

Data Index: 1776147 (The Pile)

Max Activating Token Index: 39

Text #15

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.4235. Min Act: -0.0000

Data Index: 1763511 (The Pile)

Max Activating Token Index: 16

Text #16

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.4212. Min Act: -0.0000

Data Index: 1105432 (The Pile)

Max Activating Token Index: 308

Text #17

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.4315. Min Act: -0.0000

Data Index: 1847738 (The Pile)

Max Activating Token Index: 711

Text #18

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.4312. Min Act: -0.0000

Data Index: 1555903 (The Pile)

Max Activating Token Index: 364

Text #19

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.4047. Min Act: -0.0000

Data Index: 1011045 (The Pile)

Max Activating Token Index: 119