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

Dataset: The Pile

Neuron 590 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: 1.9026. Min Range: -1.9026

Max Act: 1.9026. Min Act: -0.0000

Data Index: 1956869 (The Pile)

Max Activating Token Index: 1009

Text #1

Max Range: 1.9026. Min Range: -1.9026

Max Act: 1.5840. Min Act: -0.0000

Data Index: 1885260 (The Pile)

Max Activating Token Index: 230

Text #2

Max Range: 1.9026. Min Range: -1.9026

Max Act: 1.4667. Min Act: -0.0000

Data Index: 1979237 (The Pile)

Max Activating Token Index: 825

Text #3

Max Range: 1.9026. Min Range: -1.9026

Max Act: 1.4867. Min Act: -0.0000

Data Index: 1930672 (The Pile)

Max Activating Token Index: 283

Text #4

Max Range: 1.9026. Min Range: -1.9026

Max Act: 1.4576. Min Act: -0.0000

Data Index: 1948107 (The Pile)

Max Activating Token Index: 768

Text #5

Max Range: 1.9026. Min Range: -1.9026

Max Act: 1.3400. Min Act: -0.0000

Data Index: 1873568 (The Pile)

Max Activating Token Index: 443

Text #6

Max Range: 1.9026. Min Range: -1.9026

Max Act: 1.4118. Min Act: -0.0000

Data Index: 212662 (The Pile)

Max Activating Token Index: 576

Text #7

Max Range: 1.9026. Min Range: -1.9026

Max Act: 1.5047. Min Act: -0.0000

Data Index: 179229 (The Pile)

Max Activating Token Index: 172

Text #8

Max Range: 1.9026. Min Range: -1.9026

Max Act: 1.3708. Min Act: -0.0000

Data Index: 401063 (The Pile)

Max Activating Token Index: 833

Text #9

Max Range: 1.9026. Min Range: -1.9026

Max Act: 1.2933. Min Act: -0.0000

Data Index: 1121932 (The Pile)

Max Activating Token Index: 439

Text #10

Max Range: 1.9026. Min Range: -1.9026

Max Act: 1.1971. Min Act: -0.0000

Data Index: 1086607 (The Pile)

Max Activating Token Index: 700

Text #11

Max Range: 1.9026. Min Range: -1.9026

Max Act: 1.3358. Min Act: -0.0000

Data Index: 795309 (The Pile)

Max Activating Token Index: 333

Text #12

Max Range: 1.9026. Min Range: -1.9026

Max Act: 1.2694. Min Act: -0.0000

Data Index: 156307 (The Pile)

Max Activating Token Index: 845

Text #13

Max Range: 1.9026. Min Range: -1.9026

Max Act: 1.4254. Min Act: -0.0000

Data Index: 1166260 (The Pile)

Max Activating Token Index: 735

Text #14

Max Range: 1.9026. Min Range: -1.9026

Max Act: 1.2978. Min Act: -0.0000

Data Index: 1548819 (The Pile)

Max Activating Token Index: 218

Text #15

Max Range: 1.9026. Min Range: -1.9026

Max Act: 1.3220. Min Act: -0.0000

Data Index: 247094 (The Pile)

Max Activating Token Index: 429

Text #16

Max Range: 1.9026. Min Range: -1.9026

Max Act: 1.2036. Min Act: -0.0000

Data Index: 1874422 (The Pile)

Max Activating Token Index: 970

Text #17

Max Range: 1.9026. Min Range: -1.9026

Max Act: 1.3015. Min Act: -0.0000

Data Index: 1100400 (The Pile)

Max Activating Token Index: 1008

Text #18

Max Range: 1.9026. Min Range: -1.9026

Max Act: 1.1540. Min Act: -0.0000

Data Index: 1186439 (The Pile)

Max Activating Token Index: 217

Text #19

Max Range: 1.9026. Min Range: -1.9026

Max Act: 1.1473. Min Act: -0.0000

Data Index: 1053211 (The Pile)

Max Activating Token Index: 55