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

Dataset: The Pile

Neuron 394 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.4363. Min Act: -0.0000

Data Index: 1496367 (The Pile)

Max Activating Token Index: 915

Text #1

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.4689. Min Act: -0.0000

Data Index: 915843 (The Pile)

Max Activating Token Index: 805

Text #2

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.4521. Min Act: -0.0000

Data Index: 339854 (The Pile)

Max Activating Token Index: 825

Text #3

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.4031. Min Act: -0.0000

Data Index: 1094597 (The Pile)

Max Activating Token Index: 1019

Text #4

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.4264. Min Act: -0.0000

Data Index: 97977 (The Pile)

Max Activating Token Index: 325

Text #5

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.4473. Min Act: -0.0000

Data Index: 1092369 (The Pile)

Max Activating Token Index: 552

Text #6

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.4342. Min Act: -0.0000

Data Index: 1962729 (The Pile)

Max Activating Token Index: 246

Text #7

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.3790. Min Act: -0.0000

Data Index: 1713400 (The Pile)

Max Activating Token Index: 731

Text #8

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.3849. Min Act: -0.0000

Data Index: 80314 (The Pile)

Max Activating Token Index: 489

Text #9

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.3982. Min Act: -0.0000

Data Index: 1610258 (The Pile)

Max Activating Token Index: 148

Text #10

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.3327. Min Act: -0.0000

Data Index: 288951 (The Pile)

Max Activating Token Index: 828

Text #11

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.3554. Min Act: -0.0000

Data Index: 1132207 (The Pile)

Max Activating Token Index: 595

Text #12

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.4175. Min Act: -0.0000

Data Index: 831080 (The Pile)

Max Activating Token Index: 678

Text #13

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.3671. Min Act: -0.0000

Data Index: 14389 (The Pile)

Max Activating Token Index: 208

Text #14

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.3658. Min Act: -0.0000

Data Index: 1654574 (The Pile)

Max Activating Token Index: 869

Text #15

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.3772. Min Act: -0.0000

Data Index: 635077 (The Pile)

Max Activating Token Index: 167

Text #16

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.3625. Min Act: -0.0000

Data Index: 1265600 (The Pile)

Max Activating Token Index: 152

Text #17

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.2654. Min Act: -0.0000

Data Index: 1233596 (The Pile)

Max Activating Token Index: 706

Text #18

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.3497. Min Act: -0.0000

Data Index: 1465594 (The Pile)

Max Activating Token Index: 27

Text #19

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.3453. Min Act: -0.0000

Data Index: 823268 (The Pile)

Max Activating Token Index: 488