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

Dataset: The Pile

Neuron 2872 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4141. Min Range: -0.4141

Max Act: 0.4092. Min Act: -0.0000

Data Index: 1463608 (The Pile)

Max Activating Token Index: 237

Text #1

Max Range: 0.4141. Min Range: -0.4141

Max Act: 0.4084. Min Act: -0.0000

Data Index: 1352732 (The Pile)

Max Activating Token Index: 335

Text #2

Max Range: 0.4141. Min Range: -0.4141

Max Act: 0.4032. Min Act: -0.0000

Data Index: 573859 (The Pile)

Max Activating Token Index: 256

Text #3

Max Range: 0.4141. Min Range: -0.4141

Max Act: 0.4141. Min Act: -0.0000

Data Index: 1971337 (The Pile)

Max Activating Token Index: 608

Text #4

Max Range: 0.4141. Min Range: -0.4141

Max Act: 0.3634. Min Act: -0.0000

Data Index: 931956 (The Pile)

Max Activating Token Index: 709

Text #5

Max Range: 0.4141. Min Range: -0.4141

Max Act: 0.3500. Min Act: -0.0000

Data Index: 1222311 (The Pile)

Max Activating Token Index: 163

Text #6

Max Range: 0.4141. Min Range: -0.4141

Max Act: 0.3701. Min Act: -0.0000

Data Index: 1492712 (The Pile)

Max Activating Token Index: 63

Text #7

Max Range: 0.4141. Min Range: -0.4141

Max Act: 0.3534. Min Act: -0.0000

Data Index: 1928994 (The Pile)

Max Activating Token Index: 704

Text #8

Max Range: 0.4141. Min Range: -0.4141

Max Act: 0.3514. Min Act: -0.0000

Data Index: 1463915 (The Pile)

Max Activating Token Index: 160

Text #9

Max Range: 0.4141. Min Range: -0.4141

Max Act: 0.3309. Min Act: -0.0000

Data Index: 1749281 (The Pile)

Max Activating Token Index: 944

Text #10

Max Range: 0.4141. Min Range: -0.4141

Max Act: 0.3465. Min Act: -0.0000

Data Index: 1962805 (The Pile)

Max Activating Token Index: 429

Text #11

Max Range: 0.4141. Min Range: -0.4141

Max Act: 0.3298. Min Act: -0.0000

Data Index: 384875 (The Pile)

Max Activating Token Index: 575

Text #12

Max Range: 0.4141. Min Range: -0.4141

Max Act: 0.3285. Min Act: -0.0000

Data Index: 1990405 (The Pile)

Max Activating Token Index: 890

Text #13

Max Range: 0.4141. Min Range: -0.4141

Max Act: 0.3097. Min Act: -0.0000

Data Index: 1016340 (The Pile)

Max Activating Token Index: 85

Text #14

Max Range: 0.4141. Min Range: -0.4141

Max Act: 0.3143. Min Act: -0.0000

Data Index: 197125 (The Pile)

Max Activating Token Index: 954

Text #15

Max Range: 0.4141. Min Range: -0.4141

Max Act: 0.2978. Min Act: -0.0000

Data Index: 843842 (The Pile)

Max Activating Token Index: 603

Text #16

Max Range: 0.4141. Min Range: -0.4141

Max Act: 0.2832. Min Act: -0.0000

Data Index: 1024888 (The Pile)

Max Activating Token Index: 162

Text #17

Max Range: 0.4141. Min Range: -0.4141

Max Act: 0.3020. Min Act: -0.0000

Data Index: 69828 (The Pile)

Max Activating Token Index: 889

Text #18

Max Range: 0.4141. Min Range: -0.4141

Max Act: 0.2613. Min Act: -0.0000

Data Index: 1547952 (The Pile)

Max Activating Token Index: 692

Text #19

Max Range: 0.4141. Min Range: -0.4141

Max Act: 0.2942. Min Act: -0.0000

Data Index: 1675561 (The Pile)

Max Activating Token Index: 416