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

Dataset: The Pile

Neuron 2743 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.8205. Min Act: -0.0000

Data Index: 88071 (The Pile)

Max Activating Token Index: 705

Text #1

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.7822. Min Act: -0.0000

Data Index: 1997045 (The Pile)

Max Activating Token Index: 533

Text #2

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.6339. Min Act: -0.0000

Data Index: 784030 (The Pile)

Max Activating Token Index: 413

Text #3

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.6121. Min Act: -0.0000

Data Index: 1602036 (The Pile)

Max Activating Token Index: 193

Text #4

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.5960. Min Act: -0.0000

Data Index: 1271791 (The Pile)

Max Activating Token Index: 82

Text #5

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.5165. Min Act: -0.0000

Data Index: 929213 (The Pile)

Max Activating Token Index: 1009

Text #6

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.5388. Min Act: -0.0000

Data Index: 1355940 (The Pile)

Max Activating Token Index: 456

Text #7

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.4988. Min Act: -0.0000

Data Index: 1869001 (The Pile)

Max Activating Token Index: 78

Text #8

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.5289. Min Act: -0.0000

Data Index: 13661 (The Pile)

Max Activating Token Index: 127

Text #9

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.5389. Min Act: -0.0000

Data Index: 1102251 (The Pile)

Max Activating Token Index: 75

Text #10

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.5038. Min Act: -0.0000

Data Index: 227488 (The Pile)

Max Activating Token Index: 264

Text #11

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.5138. Min Act: -0.0000

Data Index: 954032 (The Pile)

Max Activating Token Index: 521

Text #12

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.5141. Min Act: -0.0000

Data Index: 343738 (The Pile)

Max Activating Token Index: 919

Text #13

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.5060. Min Act: -0.0000

Data Index: 1079523 (The Pile)

Max Activating Token Index: 64

Text #14

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.4977. Min Act: -0.0000

Data Index: 1973801 (The Pile)

Max Activating Token Index: 696

Text #15

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.4811. Min Act: -0.0000

Data Index: 401614 (The Pile)

Max Activating Token Index: 479

Text #16

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.4845. Min Act: -0.0000

Data Index: 1509094 (The Pile)

Max Activating Token Index: 779

Text #17

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.4751. Min Act: -0.0000

Data Index: 1878723 (The Pile)

Max Activating Token Index: 386

Text #18

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.4608. Min Act: -0.0000

Data Index: 1680625 (The Pile)

Max Activating Token Index: 869

Text #19

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.5031. Min Act: -0.0000

Data Index: 1164874 (The Pile)

Max Activating Token Index: 899