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

Dataset: The Pile

Neuron 3567 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.5906. Min Act: -0.0000

Data Index: 1461343 (The Pile)

Max Activating Token Index: 892

Text #1

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.5015. Min Act: -0.0000

Data Index: 1170024 (The Pile)

Max Activating Token Index: 521

Text #2

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4727. Min Act: -0.0000

Data Index: 1777601 (The Pile)

Max Activating Token Index: 396

Text #3

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4266. Min Act: -0.0000

Data Index: 365649 (The Pile)

Max Activating Token Index: 991

Text #4

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4036. Min Act: -0.0000

Data Index: 59076 (The Pile)

Max Activating Token Index: 717

Text #5

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.3828. Min Act: -0.0000

Data Index: 1190037 (The Pile)

Max Activating Token Index: 577

Text #6

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.3392. Min Act: -0.0000

Data Index: 1569971 (The Pile)

Max Activating Token Index: 77

Text #7

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.3751. Min Act: -0.0000

Data Index: 1190320 (The Pile)

Max Activating Token Index: 780

Text #8

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4039. Min Act: -0.0000

Data Index: 1894284 (The Pile)

Max Activating Token Index: 593

Text #9

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.3156. Min Act: -0.0000

Data Index: 1145554 (The Pile)

Max Activating Token Index: 205

Text #10

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.3350. Min Act: -0.0000

Data Index: 796061 (The Pile)

Max Activating Token Index: 738

Text #11

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.3550. Min Act: -0.0000

Data Index: 558922 (The Pile)

Max Activating Token Index: 1021

Text #12

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.3251. Min Act: -0.0000

Data Index: 1950270 (The Pile)

Max Activating Token Index: 581

Text #13

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.2761. Min Act: -0.0000

Data Index: 720623 (The Pile)

Max Activating Token Index: 993

Text #14

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.3534. Min Act: -0.0000

Data Index: 1316092 (The Pile)

Max Activating Token Index: 570

Text #15

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.3151. Min Act: -0.0000

Data Index: 73263 (The Pile)

Max Activating Token Index: 834

Text #16

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.3025. Min Act: -0.0000

Data Index: 1580140 (The Pile)

Max Activating Token Index: 839

Text #17

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.2496. Min Act: -0.0000

Data Index: 1109436 (The Pile)

Max Activating Token Index: 820

Text #18

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.2774. Min Act: -0.0000

Data Index: 1993374 (The Pile)

Max Activating Token Index: 944

Text #19

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.2861. Min Act: -0.0000

Data Index: 1390242 (The Pile)

Max Activating Token Index: 168