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

Dataset: The Pile

Neuron 4234 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.7687. Min Act: -0.0000

Data Index: 1149119 (The Pile)

Max Activating Token Index: 16

Text #1

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.6549. Min Act: -0.0000

Data Index: 1632705 (The Pile)

Max Activating Token Index: 9

Text #2

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.7253. Min Act: -0.0000

Data Index: 1090663 (The Pile)

Max Activating Token Index: 71

Text #3

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.7186. Min Act: -0.0000

Data Index: 1297038 (The Pile)

Max Activating Token Index: 93

Text #4

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.6993. Min Act: -0.0000

Data Index: 1014456 (The Pile)

Max Activating Token Index: 81

Text #5

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.6770. Min Act: -0.0000

Data Index: 639805 (The Pile)

Max Activating Token Index: 146

Text #6

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.7748. Min Act: -0.0000

Data Index: 889273 (The Pile)

Max Activating Token Index: 77

Text #7

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.7384. Min Act: -0.0000

Data Index: 881880 (The Pile)

Max Activating Token Index: 22

Text #8

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.5094. Min Act: -0.0000

Data Index: 1828513 (The Pile)

Max Activating Token Index: 93

Text #9

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.5842. Min Act: -0.0000

Data Index: 447050 (The Pile)

Max Activating Token Index: 180

Text #10

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.5697. Min Act: -0.0000

Data Index: 1565114 (The Pile)

Max Activating Token Index: 269

Text #11

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.4608. Min Act: -0.0000

Data Index: 1084901 (The Pile)

Max Activating Token Index: 124

Text #12

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.4566. Min Act: -0.0000

Data Index: 1257249 (The Pile)

Max Activating Token Index: 127

Text #13

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.5268. Min Act: -0.0000

Data Index: 1395869 (The Pile)

Max Activating Token Index: 43

Text #14

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.4256. Min Act: -0.0000

Data Index: 1516992 (The Pile)

Max Activating Token Index: 340

Text #15

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.4466. Min Act: -0.0000

Data Index: 1061201 (The Pile)

Max Activating Token Index: 74

Text #16

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.3871. Min Act: -0.0000

Data Index: 278278 (The Pile)

Max Activating Token Index: 331

Text #17

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.3884. Min Act: -0.0000

Data Index: 835908 (The Pile)

Max Activating Token Index: 25

Text #18

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.3824. Min Act: -0.0000

Data Index: 841569 (The Pile)

Max Activating Token Index: 35

Text #19

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.5275. Min Act: -0.0000

Data Index: 1381995 (The Pile)

Max Activating Token Index: 940