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

Dataset: The Pile

Neuron 4414 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5739. Min Range: -1.5739

Max Act: 1.5739. Min Act: -0.0000

Data Index: 1041053 (The Pile)

Max Activating Token Index: 297

Text #1

Max Range: 1.5739. Min Range: -1.5739

Max Act: 1.3130. Min Act: -0.0000

Data Index: 731223 (The Pile)

Max Activating Token Index: 323

Text #2

Max Range: 1.5739. Min Range: -1.5739

Max Act: 1.2213. Min Act: -0.0000

Data Index: 1168346 (The Pile)

Max Activating Token Index: 683

Text #3

Max Range: 1.5739. Min Range: -1.5739

Max Act: 1.0882. Min Act: -0.0000

Data Index: 288404 (The Pile)

Max Activating Token Index: 859

Text #4

Max Range: 1.5739. Min Range: -1.5739

Max Act: 1.0430. Min Act: -0.0000

Data Index: 66803 (The Pile)

Max Activating Token Index: 4

Text #5

Max Range: 1.5739. Min Range: -1.5739

Max Act: 1.1236. Min Act: -0.0000

Data Index: 773189 (The Pile)

Max Activating Token Index: 870

Text #6

Max Range: 1.5739. Min Range: -1.5739

Max Act: 1.0499. Min Act: -0.0000

Data Index: 1505687 (The Pile)

Max Activating Token Index: 792

Text #7

Max Range: 1.5739. Min Range: -1.5739

Max Act: 1.0083. Min Act: -0.0000

Data Index: 1063675 (The Pile)

Max Activating Token Index: 574

Text #8

Max Range: 1.5739. Min Range: -1.5739

Max Act: 1.0181. Min Act: -0.0000

Data Index: 626804 (The Pile)

Max Activating Token Index: 14

Text #9

Max Range: 1.5739. Min Range: -1.5739

Max Act: 1.0827. Min Act: -0.0000

Data Index: 1837207 (The Pile)

Max Activating Token Index: 21

Text #10

Max Range: 1.5739. Min Range: -1.5739

Max Act: 0.9750. Min Act: -0.0000

Data Index: 888404 (The Pile)

Max Activating Token Index: 420

Text #11

Max Range: 1.5739. Min Range: -1.5739

Max Act: 1.0319. Min Act: -0.0000

Data Index: 987887 (The Pile)

Max Activating Token Index: 905

Text #12

Max Range: 1.5739. Min Range: -1.5739

Max Act: 0.9955. Min Act: -0.0000

Data Index: 752728 (The Pile)

Max Activating Token Index: 462

Text #13

Max Range: 1.5739. Min Range: -1.5739

Max Act: 1.0489. Min Act: -0.0000

Data Index: 261496 (The Pile)

Max Activating Token Index: 51

Text #14

Max Range: 1.5739. Min Range: -1.5739

Max Act: 1.0189. Min Act: -0.0000

Data Index: 419455 (The Pile)

Max Activating Token Index: 834

Text #15

Max Range: 1.5739. Min Range: -1.5739

Max Act: 1.0698. Min Act: -0.0000

Data Index: 1650334 (The Pile)

Max Activating Token Index: 4

Text #16

Max Range: 1.5739. Min Range: -1.5739

Max Act: 0.9444. Min Act: -0.0000

Data Index: 612644 (The Pile)

Max Activating Token Index: 662

Text #17

Max Range: 1.5739. Min Range: -1.5739

Max Act: 0.8734. Min Act: -0.0000

Data Index: 917132 (The Pile)

Max Activating Token Index: 742

Text #18

Max Range: 1.5739. Min Range: -1.5739

Max Act: 0.9616. Min Act: -0.0000

Data Index: 1020516 (The Pile)

Max Activating Token Index: 378

Text #19

Max Range: 1.5739. Min Range: -1.5739

Max Act: 0.9852. Min Act: -0.0000

Data Index: 1831603 (The Pile)

Max Activating Token Index: 402