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

Dataset: The Pile

Neuron 4695 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: 1.8306. Min Range: -1.8306

Max Act: 1.8306. Min Act: -0.0000

Data Index: 281861 (The Pile)

Max Activating Token Index: 53

Text #1

Max Range: 1.8306. Min Range: -1.8306

Max Act: 1.3185. Min Act: -0.0000

Data Index: 599285 (The Pile)

Max Activating Token Index: 728

Text #2

Max Range: 1.8306. Min Range: -1.8306

Max Act: 1.5237. Min Act: -0.0000

Data Index: 321630 (The Pile)

Max Activating Token Index: 834

Text #3

Max Range: 1.8306. Min Range: -1.8306

Max Act: 1.5177. Min Act: -0.0000

Data Index: 1788813 (The Pile)

Max Activating Token Index: 955

Text #4

Max Range: 1.8306. Min Range: -1.8306

Max Act: 1.3950. Min Act: -0.0000

Data Index: 1639238 (The Pile)

Max Activating Token Index: 694

Text #5

Max Range: 1.8306. Min Range: -1.8306

Max Act: 1.3580. Min Act: -0.0000

Data Index: 989568 (The Pile)

Max Activating Token Index: 621

Text #6

Max Range: 1.8306. Min Range: -1.8306

Max Act: 1.2906. Min Act: -0.0000

Data Index: 1185043 (The Pile)

Max Activating Token Index: 454

Text #7

Max Range: 1.8306. Min Range: -1.8306

Max Act: 1.1791. Min Act: -0.0000

Data Index: 123774 (The Pile)

Max Activating Token Index: 445

Text #8

Max Range: 1.8306. Min Range: -1.8306

Max Act: 1.0986. Min Act: -0.0000

Data Index: 1387281 (The Pile)

Max Activating Token Index: 134

Text #9

Max Range: 1.8306. Min Range: -1.8306

Max Act: 1.0752. Min Act: -0.0000

Data Index: 1988143 (The Pile)

Max Activating Token Index: 86

Text #10

Max Range: 1.8306. Min Range: -1.8306

Max Act: 1.1705. Min Act: -0.0000

Data Index: 942058 (The Pile)

Max Activating Token Index: 559

Text #11

Max Range: 1.8306. Min Range: -1.8306

Max Act: 1.0020. Min Act: 0.0000

Data Index: 138338 (The Pile)

Max Activating Token Index: 43

Text #12

Max Range: 1.8306. Min Range: -1.8306

Max Act: 1.1109. Min Act: -0.0000

Data Index: 1465149 (The Pile)

Max Activating Token Index: 71

Text #13

Max Range: 1.8306. Min Range: -1.8306

Max Act: 1.0029. Min Act: -0.0000

Data Index: 1079507 (The Pile)

Max Activating Token Index: 659

Text #14

Max Range: 1.8306. Min Range: -1.8306

Max Act: 1.0721. Min Act: -0.0000

Data Index: 746779 (The Pile)

Max Activating Token Index: 262

Text #15

Max Range: 1.8306. Min Range: -1.8306

Max Act: 1.0583. Min Act: -0.0000

Data Index: 1540216 (The Pile)

Max Activating Token Index: 124

Text #16

Max Range: 1.8306. Min Range: -1.8306

Max Act: 0.9082. Min Act: -0.0000

Data Index: 658624 (The Pile)

Max Activating Token Index: 931

Text #17

Max Range: 1.8306. Min Range: -1.8306

Max Act: 0.9912. Min Act: -0.0000

Data Index: 1540576 (The Pile)

Max Activating Token Index: 858

Text #18

Max Range: 1.8306. Min Range: -1.8306

Max Act: 0.8765. Min Act: -0.0000

Data Index: 1583465 (The Pile)

Max Activating Token Index: 182

Text #19

Max Range: 1.8306. Min Range: -1.8306

Max Act: 0.9329. Min Act: -0.0000

Data Index: 346260 (The Pile)

Max Activating Token Index: 687