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

Dataset: The Pile

Neuron 3837 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: 0.8823. Min Range: -0.8823

Max Act: 0.8823. Min Act: -0.0000

Data Index: 1631922 (The Pile)

Max Activating Token Index: 861

Text #1

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.7279. Min Act: -0.0000

Data Index: 842313 (The Pile)

Max Activating Token Index: 766

Text #2

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.6489. Min Act: -0.0000

Data Index: 894309 (The Pile)

Max Activating Token Index: 610

Text #3

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.5443. Min Act: -0.0000

Data Index: 1196486 (The Pile)

Max Activating Token Index: 560

Text #4

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.6184. Min Act: -0.0000

Data Index: 1977882 (The Pile)

Max Activating Token Index: 876

Text #5

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.5743. Min Act: -0.0000

Data Index: 1187701 (The Pile)

Max Activating Token Index: 248

Text #6

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.5196. Min Act: -0.0000

Data Index: 728941 (The Pile)

Max Activating Token Index: 640

Text #7

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.5008. Min Act: -0.0000

Data Index: 1789161 (The Pile)

Max Activating Token Index: 825

Text #8

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.5022. Min Act: -0.0000

Data Index: 295735 (The Pile)

Max Activating Token Index: 398

Text #9

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.5108. Min Act: -0.0000

Data Index: 1521849 (The Pile)

Max Activating Token Index: 986

Text #10

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.4958. Min Act: -0.0000

Data Index: 526970 (The Pile)

Max Activating Token Index: 797

Text #11

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.4459. Min Act: -0.0000

Data Index: 1281096 (The Pile)

Max Activating Token Index: 500

Text #12

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.4213. Min Act: -0.0000

Data Index: 123267 (The Pile)

Max Activating Token Index: 202

Text #13

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.3537. Min Act: -0.0000

Data Index: 1447535 (The Pile)

Max Activating Token Index: 996

Text #14

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.4361. Min Act: -0.0000

Data Index: 499953 (The Pile)

Max Activating Token Index: 986

Text #15

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.3914. Min Act: -0.0000

Data Index: 1547592 (The Pile)

Max Activating Token Index: 624

Text #16

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.4144. Min Act: -0.0000

Data Index: 245766 (The Pile)

Max Activating Token Index: 115

Text #17

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.4568. Min Act: -0.0000

Data Index: 956407 (The Pile)

Max Activating Token Index: 929

Text #18

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.3718. Min Act: -0.0000

Data Index: 788146 (The Pile)

Max Activating Token Index: 925

Text #19

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.4192. Min Act: -0.0000

Data Index: 13805 (The Pile)

Max Activating Token Index: 980