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

Dataset: The Pile

Neuron 1806 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: 0.7914. Min Range: -0.7914

Max Act: 0.7914. Min Act: -0.0000

Data Index: 853168 (The Pile)

Max Activating Token Index: 811

Text #1

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.6375. Min Act: -0.0000

Data Index: 1016526 (The Pile)

Max Activating Token Index: 142

Text #2

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.5234. Min Act: -0.0000

Data Index: 1679278 (The Pile)

Max Activating Token Index: 301

Text #3

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.5578. Min Act: -0.0000

Data Index: 995731 (The Pile)

Max Activating Token Index: 452

Text #4

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.5203. Min Act: -0.0000

Data Index: 719544 (The Pile)

Max Activating Token Index: 926

Text #5

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.5387. Min Act: -0.0000

Data Index: 1487952 (The Pile)

Max Activating Token Index: 84

Text #6

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.5830. Min Act: -0.0000

Data Index: 846558 (The Pile)

Max Activating Token Index: 886

Text #7

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.4711. Min Act: -0.0000

Data Index: 833499 (The Pile)

Max Activating Token Index: 736

Text #8

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.4433. Min Act: -0.0000

Data Index: 566553 (The Pile)

Max Activating Token Index: 303

Text #9

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.3994. Min Act: -0.0000

Data Index: 1995741 (The Pile)

Max Activating Token Index: 341

Text #10

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.4868. Min Act: -0.0000

Data Index: 847633 (The Pile)

Max Activating Token Index: 895

Text #11

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.4447. Min Act: -0.0000

Data Index: 518373 (The Pile)

Max Activating Token Index: 162

Text #12

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.4335. Min Act: -0.0000

Data Index: 232658 (The Pile)

Max Activating Token Index: 169

Text #13

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.4091. Min Act: -0.0000

Data Index: 350312 (The Pile)

Max Activating Token Index: 199

Text #14

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.3771. Min Act: -0.0000

Data Index: 1975980 (The Pile)

Max Activating Token Index: 139

Text #15

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.3405. Min Act: -0.0000

Data Index: 1833864 (The Pile)

Max Activating Token Index: 184

Text #16

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.3075. Min Act: -0.0000

Data Index: 1370192 (The Pile)

Max Activating Token Index: 213

Text #17

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.3730. Min Act: -0.0000

Data Index: 1601471 (The Pile)

Max Activating Token Index: 96

Text #18

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.3085. Min Act: -0.0000

Data Index: 1449309 (The Pile)

Max Activating Token Index: 17

Text #19

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.2986. Min Act: -0.0000

Data Index: 1358406 (The Pile)

Max Activating Token Index: 807