Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1957 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.3814. Min Act: -0.0000

Data Index: 1140078 (The Pile)

Max Activating Token Index: 235

Text #1

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.5786. Min Act: -0.0000

Data Index: 1732963 (The Pile)

Max Activating Token Index: 322

Text #2

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.4919. Min Act: -0.0000

Data Index: 1138294 (The Pile)

Max Activating Token Index: 845

Text #3

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.4414. Min Act: -0.0000

Data Index: 532715 (The Pile)

Max Activating Token Index: 163

Text #4

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.5241. Min Act: -0.0000

Data Index: 527757 (The Pile)

Max Activating Token Index: 255

Text #5

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.2793. Min Act: -0.0000

Data Index: 178806 (The Pile)

Max Activating Token Index: 582

Text #6

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.4120. Min Act: -0.0000

Data Index: 706115 (The Pile)

Max Activating Token Index: 893

Text #7

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.4131. Min Act: -0.0000

Data Index: 129837 (The Pile)

Max Activating Token Index: 938

Text #8

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.4094. Min Act: -0.0000

Data Index: 539116 (The Pile)

Max Activating Token Index: 129

Text #9

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.3321. Min Act: -0.0000

Data Index: 143220 (The Pile)

Max Activating Token Index: 908

Text #10

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.2868. Min Act: -0.0000

Data Index: 1514640 (The Pile)

Max Activating Token Index: 636

Text #11

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.3475. Min Act: -0.0000

Data Index: 954766 (The Pile)

Max Activating Token Index: 808

Text #12

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.3024. Min Act: -0.0000

Data Index: 1016456 (The Pile)

Max Activating Token Index: 22

Text #13

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.2618. Min Act: -0.0000

Data Index: 1987051 (The Pile)

Max Activating Token Index: 654

Text #14

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.3199. Min Act: -0.0000

Data Index: 79264 (The Pile)

Max Activating Token Index: 503

Text #15

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.3511. Min Act: -0.0000

Data Index: 1444554 (The Pile)

Max Activating Token Index: 584

Text #16

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.3882. Min Act: -0.0000

Data Index: 8081 (The Pile)

Max Activating Token Index: 640

Text #17

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.2840. Min Act: -0.0000

Data Index: 675193 (The Pile)

Max Activating Token Index: 640

Text #18

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.3297. Min Act: -0.0000

Data Index: 1164590 (The Pile)

Max Activating Token Index: 114

Text #19

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.2435. Min Act: -0.0000

Data Index: 1541370 (The Pile)

Max Activating Token Index: 256