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

Dataset: The Pile

Neuron 1776 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.3969. Min Act: -0.0000

Data Index: 1753120 (The Pile)

Max Activating Token Index: 484

Text #1

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.3674. Min Act: -0.0000

Data Index: 1559514 (The Pile)

Max Activating Token Index: 291

Text #2

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.3738. Min Act: -0.0000

Data Index: 594506 (The Pile)

Max Activating Token Index: 151

Text #3

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.3172. Min Act: -0.0000

Data Index: 1065175 (The Pile)

Max Activating Token Index: 18

Text #4

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.3188. Min Act: -0.0000

Data Index: 1446566 (The Pile)

Max Activating Token Index: 633

Text #5

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.2880. Min Act: -0.0000

Data Index: 234481 (The Pile)

Max Activating Token Index: 195

Text #6

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.2865. Min Act: -0.0000

Data Index: 979744 (The Pile)

Max Activating Token Index: 894

Text #7

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.2809. Min Act: -0.0000

Data Index: 453935 (The Pile)

Max Activating Token Index: 617

Text #8

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.2755. Min Act: -0.0000

Data Index: 1738441 (The Pile)

Max Activating Token Index: 363

Text #9

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.2742. Min Act: -0.0000

Data Index: 344837 (The Pile)

Max Activating Token Index: 285

Text #10

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.2492. Min Act: -0.0000

Data Index: 1556606 (The Pile)

Max Activating Token Index: 333

Text #11

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.2521. Min Act: -0.0000

Data Index: 661741 (The Pile)

Max Activating Token Index: 521

Text #12

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.2634. Min Act: -0.0000

Data Index: 145434 (The Pile)

Max Activating Token Index: 371

Text #13

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.2573. Min Act: -0.0000

Data Index: 352301 (The Pile)

Max Activating Token Index: 35

Text #14

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.2641. Min Act: -0.0000

Data Index: 1147043 (The Pile)

Max Activating Token Index: 758

Text #15

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.2590. Min Act: -0.0000

Data Index: 453834 (The Pile)

Max Activating Token Index: 276

Text #16

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.2378. Min Act: -0.0000

Data Index: 119615 (The Pile)

Max Activating Token Index: 10

Text #17

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.2382. Min Act: -0.0000

Data Index: 990445 (The Pile)

Max Activating Token Index: 87

Text #18

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.2527. Min Act: -0.0000

Data Index: 63203 (The Pile)

Max Activating Token Index: 355

Text #19

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.2194. Min Act: -0.0000

Data Index: 322310 (The Pile)

Max Activating Token Index: 134