Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 432 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.5448. Min Act: -0.0000

Data Index: 889706 (The Pile)

Max Activating Token Index: 313

Text #1

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.5581. Min Act: -0.0000

Data Index: 330702 (The Pile)

Max Activating Token Index: 102

Text #2

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.3948. Min Act: -0.0000

Data Index: 144674 (The Pile)

Max Activating Token Index: 103

Text #3

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.5425. Min Act: -0.0000

Data Index: 777490 (The Pile)

Max Activating Token Index: 819

Text #4

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.5723. Min Act: -0.0000

Data Index: 476728 (The Pile)

Max Activating Token Index: 376

Text #5

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.5341. Min Act: -0.0000

Data Index: 1491581 (The Pile)

Max Activating Token Index: 834

Text #6

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.4652. Min Act: -0.0000

Data Index: 1122948 (The Pile)

Max Activating Token Index: 610

Text #7

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.4916. Min Act: -0.0000

Data Index: 1797266 (The Pile)

Max Activating Token Index: 229

Text #8

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.4554. Min Act: -0.0000

Data Index: 890505 (The Pile)

Max Activating Token Index: 933

Text #9

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.4512. Min Act: -0.0000

Data Index: 550600 (The Pile)

Max Activating Token Index: 747

Text #10

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.3669. Min Act: -0.0000

Data Index: 442772 (The Pile)

Max Activating Token Index: 131

Text #11

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.5470. Min Act: -0.0000

Data Index: 1171895 (The Pile)

Max Activating Token Index: 219

Text #12

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.4729. Min Act: -0.0000

Data Index: 330255 (The Pile)

Max Activating Token Index: 203

Text #13

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.5017. Min Act: -0.0000

Data Index: 484472 (The Pile)

Max Activating Token Index: 825

Text #14

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.4470. Min Act: -0.0000

Data Index: 872359 (The Pile)

Max Activating Token Index: 487

Text #15

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.4754. Min Act: -0.0000

Data Index: 1544916 (The Pile)

Max Activating Token Index: 248

Text #16

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.2965. Min Act: -0.0000

Data Index: 1334257 (The Pile)

Max Activating Token Index: 433

Text #17

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.4071. Min Act: -0.0000

Data Index: 1407385 (The Pile)

Max Activating Token Index: 850

Text #18

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.3731. Min Act: -0.0000

Data Index: 907664 (The Pile)

Max Activating Token Index: 903

Text #19

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.5416. Min Act: -0.0000

Data Index: 1560383 (The Pile)

Max Activating Token Index: 714