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

Dataset: The Pile

Neuron 1309 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.5003. Min Act: -0.0000

Data Index: 33427 (The Pile)

Max Activating Token Index: 488

Text #1

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.4912. Min Act: -0.0000

Data Index: 1723374 (The Pile)

Max Activating Token Index: 19

Text #2

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.5229. Min Act: -0.0000

Data Index: 595265 (The Pile)

Max Activating Token Index: 946

Text #3

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.4840. Min Act: -0.0000

Data Index: 1466848 (The Pile)

Max Activating Token Index: 735

Text #4

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.4979. Min Act: -0.0000

Data Index: 1648495 (The Pile)

Max Activating Token Index: 144

Text #5

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.4257. Min Act: -0.0000

Data Index: 1481577 (The Pile)

Max Activating Token Index: 33

Text #6

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.4087. Min Act: -0.0000

Data Index: 83693 (The Pile)

Max Activating Token Index: 847

Text #7

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.4348. Min Act: -0.0000

Data Index: 998200 (The Pile)

Max Activating Token Index: 63

Text #8

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.4328. Min Act: -0.0000

Data Index: 666217 (The Pile)

Max Activating Token Index: 59

Text #9

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.4117. Min Act: -0.0000

Data Index: 1582398 (The Pile)

Max Activating Token Index: 81

Text #10

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.4441. Min Act: -0.0000

Data Index: 505929 (The Pile)

Max Activating Token Index: 747

Text #11

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.3915. Min Act: -0.0000

Data Index: 1529520 (The Pile)

Max Activating Token Index: 29

Text #12

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.3865. Min Act: -0.0000

Data Index: 1742514 (The Pile)

Max Activating Token Index: 87

Text #13

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.3988. Min Act: -0.0000

Data Index: 1413064 (The Pile)

Max Activating Token Index: 80

Text #14

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.4137. Min Act: -0.0000

Data Index: 1963873 (The Pile)

Max Activating Token Index: 24

Text #15

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.3857. Min Act: -0.0000

Data Index: 1594324 (The Pile)

Max Activating Token Index: 627

Text #16

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.4093. Min Act: -0.0000

Data Index: 305656 (The Pile)

Max Activating Token Index: 27

Text #17

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.4064. Min Act: -0.0000

Data Index: 1205131 (The Pile)

Max Activating Token Index: 221

Text #18

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.4072. Min Act: -0.0000

Data Index: 1674838 (The Pile)

Max Activating Token Index: 27

Text #19

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.4330. Min Act: -0.0000

Data Index: 173233 (The Pile)

Max Activating Token Index: 109