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

Dataset: The Pile

Neuron 4375 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: 0.8053. Min Range: -0.8053

Max Act: 0.7688. Min Act: -0.0000

Data Index: 1545652 (The Pile)

Max Activating Token Index: 26

Text #1

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.5754. Min Act: -0.0000

Data Index: 312632 (The Pile)

Max Activating Token Index: 94

Text #2

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.7445. Min Act: -0.0000

Data Index: 835802 (The Pile)

Max Activating Token Index: 24

Text #3

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.7520. Min Act: -0.0000

Data Index: 1244722 (The Pile)

Max Activating Token Index: 32

Text #4

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.6936. Min Act: -0.0000

Data Index: 1351355 (The Pile)

Max Activating Token Index: 12

Text #5

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.7764. Min Act: -0.0000

Data Index: 668042 (The Pile)

Max Activating Token Index: 42

Text #6

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.8053. Min Act: -0.0000

Data Index: 1088448 (The Pile)

Max Activating Token Index: 151

Text #7

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.6235. Min Act: -0.0000

Data Index: 818092 (The Pile)

Max Activating Token Index: 677

Text #8

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.6451. Min Act: -0.0000

Data Index: 826263 (The Pile)

Max Activating Token Index: 12

Text #9

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.6145. Min Act: -0.0000

Data Index: 1854391 (The Pile)

Max Activating Token Index: 587

Text #10

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.7171. Min Act: -0.0000

Data Index: 839181 (The Pile)

Max Activating Token Index: 537

Text #11

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.7162. Min Act: -0.0000

Data Index: 176663 (The Pile)

Max Activating Token Index: 39

Text #12

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.6312. Min Act: -0.0000

Data Index: 948229 (The Pile)

Max Activating Token Index: 190

Text #13

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.4334. Min Act: -0.0000

Data Index: 902001 (The Pile)

Max Activating Token Index: 118

Text #14

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.5441. Min Act: -0.0000

Data Index: 202365 (The Pile)

Max Activating Token Index: 281

Text #15

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.6367. Min Act: -0.0000

Data Index: 114226 (The Pile)

Max Activating Token Index: 267

Text #16

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.5818. Min Act: -0.0000

Data Index: 676349 (The Pile)

Max Activating Token Index: 845

Text #17

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.5831. Min Act: -0.0000

Data Index: 1577402 (The Pile)

Max Activating Token Index: 951

Text #18

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.5533. Min Act: -0.0000

Data Index: 1132286 (The Pile)

Max Activating Token Index: 696

Text #19

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.4336. Min Act: -0.0000

Data Index: 1685860 (The Pile)

Max Activating Token Index: 203