Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3457 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 12.0058. Min Range: -12.0058

Max Act: 12.0058. Min Act: -0.0000

Data Index: 1666391 (The Pile)

Max Activating Token Index: 96

Text #1

Max Range: 12.0058. Min Range: -12.0058

Max Act: 11.0294. Min Act: -0.0000

Data Index: 1831192 (The Pile)

Max Activating Token Index: 288

Text #2

Max Range: 12.0058. Min Range: -12.0058

Max Act: 11.3244. Min Act: -0.0000

Data Index: 7732 (The Pile)

Max Activating Token Index: 50

Text #3

Max Range: 12.0058. Min Range: -12.0058

Max Act: 11.0384. Min Act: -0.0000

Data Index: 1950416 (The Pile)

Max Activating Token Index: 41

Text #4

Max Range: 12.0058. Min Range: -12.0058

Max Act: 11.1209. Min Act: -0.0000

Data Index: 1261941 (The Pile)

Max Activating Token Index: 148

Text #5

Max Range: 12.0058. Min Range: -12.0058

Max Act: 10.5887. Min Act: -0.0000

Data Index: 419347 (The Pile)

Max Activating Token Index: 104

Text #6

Max Range: 12.0058. Min Range: -12.0058

Max Act: 10.5981. Min Act: -0.0000

Data Index: 1994498 (The Pile)

Max Activating Token Index: 70

Text #7

Max Range: 12.0058. Min Range: -12.0058

Max Act: 10.0327. Min Act: -0.0000

Data Index: 856679 (The Pile)

Max Activating Token Index: 193

Text #8

Max Range: 12.0058. Min Range: -12.0058

Max Act: 9.9852. Min Act: -0.0000

Data Index: 420710 (The Pile)

Max Activating Token Index: 813

Text #9

Max Range: 12.0058. Min Range: -12.0058

Max Act: 10.4532. Min Act: -0.0000

Data Index: 1002313 (The Pile)

Max Activating Token Index: 53

Text #10

Max Range: 12.0058. Min Range: -12.0058

Max Act: 10.1759. Min Act: -0.0000

Data Index: 1470262 (The Pile)

Max Activating Token Index: 263

Text #11

Max Range: 12.0058. Min Range: -12.0058

Max Act: 10.0123. Min Act: -0.0000

Data Index: 168958 (The Pile)

Max Activating Token Index: 120

Text #12

Max Range: 12.0058. Min Range: -12.0058

Max Act: 9.6094. Min Act: -0.0000

Data Index: 1244110 (The Pile)

Max Activating Token Index: 649

Text #13

Max Range: 12.0058. Min Range: -12.0058

Max Act: 9.5644. Min Act: -0.0000

Data Index: 600937 (The Pile)

Max Activating Token Index: 211

Text #14

Max Range: 12.0058. Min Range: -12.0058

Max Act: 10.0086. Min Act: -0.0000

Data Index: 662406 (The Pile)

Max Activating Token Index: 452

Text #15

Max Range: 12.0058. Min Range: -12.0058

Max Act: 9.9886. Min Act: -0.0000

Data Index: 775013 (The Pile)

Max Activating Token Index: 610

Text #16

Max Range: 12.0058. Min Range: -12.0058

Max Act: 10.3603. Min Act: -0.0000

Data Index: 1718689 (The Pile)

Max Activating Token Index: 135

Text #17

Max Range: 12.0058. Min Range: -12.0058

Max Act: 9.8399. Min Act: -0.0000

Data Index: 1898715 (The Pile)

Max Activating Token Index: 861

Text #18

Max Range: 12.0058. Min Range: -12.0058

Max Act: 9.2206. Min Act: -0.0000

Data Index: 1844025 (The Pile)

Max Activating Token Index: 955

Text #19

Max Range: 12.0058. Min Range: -12.0058

Max Act: 10.0047. Min Act: -0.0000

Data Index: 1428655 (The Pile)

Max Activating Token Index: 558