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

Dataset: The Pile

Neuron 1531 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: 0.5736. Min Range: -0.5736

Max Act: 0.5736. Min Act: -0.0000

Data Index: 1244481 (The Pile)

Max Activating Token Index: 23

Text #1

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.5695. Min Act: -0.0000

Data Index: 1592974 (The Pile)

Max Activating Token Index: 68

Text #2

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.5468. Min Act: -0.0000

Data Index: 158778 (The Pile)

Max Activating Token Index: 9

Text #3

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.5303. Min Act: -0.0000

Data Index: 1032092 (The Pile)

Max Activating Token Index: 68

Text #4

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.4872. Min Act: -0.0000

Data Index: 909302 (The Pile)

Max Activating Token Index: 540

Text #5

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.4840. Min Act: -0.0000

Data Index: 678970 (The Pile)

Max Activating Token Index: 124

Text #6

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.4837. Min Act: -0.0000

Data Index: 16408 (The Pile)

Max Activating Token Index: 71

Text #7

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.5031. Min Act: -0.0000

Data Index: 643102 (The Pile)

Max Activating Token Index: 15

Text #8

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.5047. Min Act: -0.0000

Data Index: 1341245 (The Pile)

Max Activating Token Index: 259

Text #9

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.4633. Min Act: -0.0000

Data Index: 647375 (The Pile)

Max Activating Token Index: 52

Text #10

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.4672. Min Act: -0.0000

Data Index: 1487162 (The Pile)

Max Activating Token Index: 19

Text #11

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.4642. Min Act: -0.0000

Data Index: 1538605 (The Pile)

Max Activating Token Index: 7

Text #12

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.4642. Min Act: -0.0000

Data Index: 1332886 (The Pile)

Max Activating Token Index: 7

Text #13

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.4476. Min Act: -0.0000

Data Index: 1465891 (The Pile)

Max Activating Token Index: 16

Text #14

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.4574. Min Act: -0.0000

Data Index: 1112654 (The Pile)

Max Activating Token Index: 34

Text #15

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.4835. Min Act: -0.0000

Data Index: 775488 (The Pile)

Max Activating Token Index: 19

Text #16

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.4540. Min Act: -0.0000

Data Index: 457774 (The Pile)

Max Activating Token Index: 41

Text #17

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.4204. Min Act: -0.0000

Data Index: 37967 (The Pile)

Max Activating Token Index: 25

Text #18

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.4082. Min Act: -0.0000

Data Index: 90911 (The Pile)

Max Activating Token Index: 14

Text #19

Max Range: 0.5736. Min Range: -0.5736

Max Act: 0.4857. Min Act: -0.0000

Data Index: 1987159 (The Pile)

Max Activating Token Index: 462