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

Dataset: The Pile

Neuron 1361 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.4800. Min Act: -0.0000

Data Index: 1913846 (The Pile)

Max Activating Token Index: 229

Text #1

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.4450. Min Act: -0.0000

Data Index: 1834785 (The Pile)

Max Activating Token Index: 977

Text #2

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.3834. Min Act: -0.0000

Data Index: 1448092 (The Pile)

Max Activating Token Index: 281

Text #3

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.4061. Min Act: -0.0000

Data Index: 1953612 (The Pile)

Max Activating Token Index: 874

Text #4

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.4129. Min Act: -0.0000

Data Index: 372082 (The Pile)

Max Activating Token Index: 360

Text #5

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.4099. Min Act: -0.0000

Data Index: 181891 (The Pile)

Max Activating Token Index: 568

Text #6

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.3797. Min Act: -0.0000

Data Index: 715729 (The Pile)

Max Activating Token Index: 536

Text #7

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.3857. Min Act: -0.0000

Data Index: 1304106 (The Pile)

Max Activating Token Index: 513

Text #8

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.3523. Min Act: -0.0000

Data Index: 1917492 (The Pile)

Max Activating Token Index: 143

Text #9

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.3585. Min Act: -0.0000

Data Index: 1673744 (The Pile)

Max Activating Token Index: 439

Text #10

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.3484. Min Act: -0.0000

Data Index: 1348496 (The Pile)

Max Activating Token Index: 522

Text #11

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.3910. Min Act: -0.0000

Data Index: 294596 (The Pile)

Max Activating Token Index: 178

Text #12

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.3355. Min Act: -0.0000

Data Index: 943996 (The Pile)

Max Activating Token Index: 88

Text #13

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.3151. Min Act: -0.0000

Data Index: 1059512 (The Pile)

Max Activating Token Index: 129

Text #14

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.3432. Min Act: -0.0000

Data Index: 1078872 (The Pile)

Max Activating Token Index: 375

Text #15

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.3183. Min Act: -0.0000

Data Index: 1740778 (The Pile)

Max Activating Token Index: 103

Text #16

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.2972. Min Act: -0.0000

Data Index: 509022 (The Pile)

Max Activating Token Index: 791

Text #17

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.3046. Min Act: -0.0000

Data Index: 39724 (The Pile)

Max Activating Token Index: 93

Text #18

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.3299. Min Act: -0.0000

Data Index: 1183586 (The Pile)

Max Activating Token Index: 987

Text #19

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.3166. Min Act: -0.0000

Data Index: 1743939 (The Pile)

Max Activating Token Index: 126