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

Dataset: The Pile

Neuron 1210 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: 0.6440. Min Range: -0.6440

Max Act: 0.6440. Min Act: -0.0000

Data Index: 840868 (The Pile)

Max Activating Token Index: 551

Text #1

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.5447. Min Act: -0.0000

Data Index: 1839819 (The Pile)

Max Activating Token Index: 247

Text #2

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4706. Min Act: -0.0000

Data Index: 1072865 (The Pile)

Max Activating Token Index: 450

Text #3

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4411. Min Act: -0.0000

Data Index: 792256 (The Pile)

Max Activating Token Index: 127

Text #4

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.5010. Min Act: -0.0000

Data Index: 51011 (The Pile)

Max Activating Token Index: 46

Text #5

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4395. Min Act: -0.0000

Data Index: 1220070 (The Pile)

Max Activating Token Index: 465

Text #6

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4362. Min Act: -0.0000

Data Index: 1279511 (The Pile)

Max Activating Token Index: 661

Text #7

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4349. Min Act: -0.0000

Data Index: 1621074 (The Pile)

Max Activating Token Index: 442

Text #8

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4176. Min Act: -0.0000

Data Index: 1930926 (The Pile)

Max Activating Token Index: 37

Text #9

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4126. Min Act: -0.0000

Data Index: 655809 (The Pile)

Max Activating Token Index: 452

Text #10

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4498. Min Act: -0.0000

Data Index: 90703 (The Pile)

Max Activating Token Index: 897

Text #11

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4488. Min Act: -0.0000

Data Index: 1719478 (The Pile)

Max Activating Token Index: 509

Text #12

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.3865. Min Act: -0.0000

Data Index: 1767533 (The Pile)

Max Activating Token Index: 505

Text #13

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.3699. Min Act: -0.0000

Data Index: 1498166 (The Pile)

Max Activating Token Index: 699

Text #14

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.3852. Min Act: -0.0000

Data Index: 1396842 (The Pile)

Max Activating Token Index: 375

Text #15

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4011. Min Act: -0.0000

Data Index: 1906591 (The Pile)

Max Activating Token Index: 333

Text #16

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.3816. Min Act: -0.0000

Data Index: 78457 (The Pile)

Max Activating Token Index: 206

Text #17

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.3883. Min Act: -0.0000

Data Index: 108904 (The Pile)

Max Activating Token Index: 752

Text #18

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4037. Min Act: -0.0000

Data Index: 547817 (The Pile)

Max Activating Token Index: 391

Text #19

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4018. Min Act: -0.0000

Data Index: 776304 (The Pile)

Max Activating Token Index: 96