Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2435 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.5031. Min Act: -0.0000

Data Index: 1744953 (The Pile)

Max Activating Token Index: 794

Text #1

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4825. Min Act: -0.0000

Data Index: 526106 (The Pile)

Max Activating Token Index: 915

Text #2

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4157. Min Act: -0.0000

Data Index: 1102274 (The Pile)

Max Activating Token Index: 163

Text #3

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.3673. Min Act: -0.0000

Data Index: 1466554 (The Pile)

Max Activating Token Index: 278

Text #4

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.3232. Min Act: -0.0000

Data Index: 74957 (The Pile)

Max Activating Token Index: 237

Text #5

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.3507. Min Act: -0.0000

Data Index: 513810 (The Pile)

Max Activating Token Index: 1005

Text #6

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.2893. Min Act: -0.0000

Data Index: 295205 (The Pile)

Max Activating Token Index: 127

Text #7

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.3261. Min Act: -0.0000

Data Index: 678712 (The Pile)

Max Activating Token Index: 844

Text #8

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.3177. Min Act: -0.0000

Data Index: 509251 (The Pile)

Max Activating Token Index: 943

Text #9

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.3307. Min Act: -0.0000

Data Index: 1725714 (The Pile)

Max Activating Token Index: 878

Text #10

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.2598. Min Act: -0.0000

Data Index: 1104258 (The Pile)

Max Activating Token Index: 1014

Text #11

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.3423. Min Act: -0.0000

Data Index: 367745 (The Pile)

Max Activating Token Index: 722

Text #12

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.2550. Min Act: -0.0000

Data Index: 1721831 (The Pile)

Max Activating Token Index: 577

Text #13

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.3760. Min Act: -0.0000

Data Index: 98311 (The Pile)

Max Activating Token Index: 957

Text #14

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.3149. Min Act: -0.0000

Data Index: 1314441 (The Pile)

Max Activating Token Index: 762

Text #15

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.2068. Min Act: 0.0000

Data Index: 1906766 (The Pile)

Max Activating Token Index: 606

Text #16

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.2512. Min Act: -0.0000

Data Index: 271530 (The Pile)

Max Activating Token Index: 101

Text #17

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.2519. Min Act: -0.0000

Data Index: 1481863 (The Pile)

Max Activating Token Index: 443

Text #18

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.2876. Min Act: -0.0000

Data Index: 751309 (The Pile)

Max Activating Token Index: 301

Text #19

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.2701. Min Act: -0.0000

Data Index: 252949 (The Pile)

Max Activating Token Index: 647