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

Dataset: The Pile

Neuron 2103 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: 4.0177. Min Range: -4.0177

Max Act: 4.0177. Min Act: -0.0000

Data Index: 1198081 (The Pile)

Max Activating Token Index: 345

Text #1

Max Range: 4.0177. Min Range: -4.0177

Max Act: 3.9734. Min Act: -0.0000

Data Index: 1429542 (The Pile)

Max Activating Token Index: 292

Text #2

Max Range: 4.0177. Min Range: -4.0177

Max Act: 3.4612. Min Act: -0.0000

Data Index: 1127281 (The Pile)

Max Activating Token Index: 680

Text #3

Max Range: 4.0177. Min Range: -4.0177

Max Act: 3.6769. Min Act: -0.0000

Data Index: 282488 (The Pile)

Max Activating Token Index: 707

Text #4

Max Range: 4.0177. Min Range: -4.0177

Max Act: 3.9521. Min Act: -0.0000

Data Index: 1772481 (The Pile)

Max Activating Token Index: 8

Text #5

Max Range: 4.0177. Min Range: -4.0177

Max Act: 3.4995. Min Act: -0.0000

Data Index: 729436 (The Pile)

Max Activating Token Index: 1019

Text #6

Max Range: 4.0177. Min Range: -4.0177

Max Act: 3.7514. Min Act: -0.0000

Data Index: 1047925 (The Pile)

Max Activating Token Index: 771

Text #7

Max Range: 4.0177. Min Range: -4.0177

Max Act: 3.6512. Min Act: -0.0000

Data Index: 1748033 (The Pile)

Max Activating Token Index: 357

Text #8

Max Range: 4.0177. Min Range: -4.0177

Max Act: 3.1159. Min Act: -0.0000

Data Index: 671821 (The Pile)

Max Activating Token Index: 906

Text #9

Max Range: 4.0177. Min Range: -4.0177

Max Act: 3.7279. Min Act: -0.0000

Data Index: 986850 (The Pile)

Max Activating Token Index: 62

Text #10

Max Range: 4.0177. Min Range: -4.0177

Max Act: 3.7049. Min Act: -0.0000

Data Index: 539934 (The Pile)

Max Activating Token Index: 438

Text #11

Max Range: 4.0177. Min Range: -4.0177

Max Act: 3.6129. Min Act: -0.0000

Data Index: 1575231 (The Pile)

Max Activating Token Index: 509

Text #12

Max Range: 4.0177. Min Range: -4.0177

Max Act: 3.5692. Min Act: -0.0000

Data Index: 1821770 (The Pile)

Max Activating Token Index: 803

Text #13

Max Range: 4.0177. Min Range: -4.0177

Max Act: 3.7071. Min Act: -0.0000

Data Index: 1947713 (The Pile)

Max Activating Token Index: 489

Text #14

Max Range: 4.0177. Min Range: -4.0177

Max Act: 3.7100. Min Act: -0.0000

Data Index: 650032 (The Pile)

Max Activating Token Index: 133

Text #15

Max Range: 4.0177. Min Range: -4.0177

Max Act: 3.5201. Min Act: -0.0000

Data Index: 525315 (The Pile)

Max Activating Token Index: 414

Text #16

Max Range: 4.0177. Min Range: -4.0177

Max Act: 3.2005. Min Act: -0.0000

Data Index: 1300833 (The Pile)

Max Activating Token Index: 728

Text #17

Max Range: 4.0177. Min Range: -4.0177

Max Act: 3.6307. Min Act: -0.0000

Data Index: 698469 (The Pile)

Max Activating Token Index: 414

Text #18

Max Range: 4.0177. Min Range: -4.0177

Max Act: 3.4492. Min Act: -0.0000

Data Index: 806267 (The Pile)

Max Activating Token Index: 754

Text #19

Max Range: 4.0177. Min Range: -4.0177

Max Act: 3.4669. Min Act: -0.0000

Data Index: 1838565 (The Pile)

Max Activating Token Index: 872