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

Dataset: The Pile

Neuron 4935 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: 0.4786. Min Range: -0.4786

Max Act: 0.4786. Min Act: -0.0000

Data Index: 1520962 (The Pile)

Max Activating Token Index: 1006

Text #1

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.4197. Min Act: -0.0000

Data Index: 1949593 (The Pile)

Max Activating Token Index: 397

Text #2

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3666. Min Act: -0.0000

Data Index: 1327299 (The Pile)

Max Activating Token Index: 591

Text #3

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3908. Min Act: -0.0000

Data Index: 1083746 (The Pile)

Max Activating Token Index: 548

Text #4

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3849. Min Act: -0.0000

Data Index: 86245 (The Pile)

Max Activating Token Index: 120

Text #5

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3136. Min Act: -0.0000

Data Index: 994540 (The Pile)

Max Activating Token Index: 990

Text #6

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3463. Min Act: -0.0000

Data Index: 1075644 (The Pile)

Max Activating Token Index: 73

Text #7

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3479. Min Act: -0.0000

Data Index: 1547645 (The Pile)

Max Activating Token Index: 789

Text #8

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3244. Min Act: -0.0000

Data Index: 1228816 (The Pile)

Max Activating Token Index: 45

Text #9

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.2904. Min Act: -0.0000

Data Index: 525839 (The Pile)

Max Activating Token Index: 822

Text #10

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3180. Min Act: -0.0000

Data Index: 128232 (The Pile)

Max Activating Token Index: 841

Text #11

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3025. Min Act: -0.0000

Data Index: 134141 (The Pile)

Max Activating Token Index: 961

Text #12

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3083. Min Act: -0.0000

Data Index: 278246 (The Pile)

Max Activating Token Index: 861

Text #13

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3107. Min Act: -0.0000

Data Index: 1095592 (The Pile)

Max Activating Token Index: 673

Text #14

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3297. Min Act: -0.0000

Data Index: 221147 (The Pile)

Max Activating Token Index: 904

Text #15

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3084. Min Act: -0.0000

Data Index: 432416 (The Pile)

Max Activating Token Index: 910

Text #16

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.2816. Min Act: -0.0000

Data Index: 788157 (The Pile)

Max Activating Token Index: 990

Text #17

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.2966. Min Act: -0.0000

Data Index: 1790961 (The Pile)

Max Activating Token Index: 575

Text #18

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3039. Min Act: -0.0000

Data Index: 1684783 (The Pile)

Max Activating Token Index: 205

Text #19

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.2768. Min Act: -0.0000

Data Index: 34714 (The Pile)

Max Activating Token Index: 237