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

Dataset: The Pile

Neuron 4661 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.4953. Min Act: -0.0000

Data Index: 1761469 (The Pile)

Max Activating Token Index: 32

Text #1

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.4726. Min Act: -0.0000

Data Index: 1615852 (The Pile)

Max Activating Token Index: 219

Text #2

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.4614. Min Act: -0.0000

Data Index: 87909 (The Pile)

Max Activating Token Index: 440

Text #3

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.4404. Min Act: -0.0000

Data Index: 1737440 (The Pile)

Max Activating Token Index: 243

Text #4

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.4545. Min Act: -0.0000

Data Index: 643737 (The Pile)

Max Activating Token Index: 758

Text #5

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.4012. Min Act: -0.0000

Data Index: 276377 (The Pile)

Max Activating Token Index: 890

Text #6

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3859. Min Act: -0.0000

Data Index: 574896 (The Pile)

Max Activating Token Index: 577

Text #7

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.4101. Min Act: -0.0000

Data Index: 1575521 (The Pile)

Max Activating Token Index: 403

Text #8

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.4274. Min Act: -0.0000

Data Index: 895405 (The Pile)

Max Activating Token Index: 1001

Text #9

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.4032. Min Act: -0.0000

Data Index: 933140 (The Pile)

Max Activating Token Index: 382

Text #10

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.4038. Min Act: -0.0000

Data Index: 1434885 (The Pile)

Max Activating Token Index: 491

Text #11

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.4011. Min Act: -0.0000

Data Index: 1590129 (The Pile)

Max Activating Token Index: 313

Text #12

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3638. Min Act: -0.0000

Data Index: 601208 (The Pile)

Max Activating Token Index: 649

Text #13

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3723. Min Act: -0.0000

Data Index: 1593043 (The Pile)

Max Activating Token Index: 91

Text #14

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3978. Min Act: -0.0000

Data Index: 1883738 (The Pile)

Max Activating Token Index: 518

Text #15

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3925. Min Act: -0.0000

Data Index: 523616 (The Pile)

Max Activating Token Index: 955

Text #16

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3736. Min Act: -0.0000

Data Index: 661646 (The Pile)

Max Activating Token Index: 452

Text #17

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3800. Min Act: -0.0000

Data Index: 95625 (The Pile)

Max Activating Token Index: 805

Text #18

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3706. Min Act: -0.0000

Data Index: 832841 (The Pile)

Max Activating Token Index: 676

Text #19

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3470. Min Act: -0.0000

Data Index: 1004296 (The Pile)

Max Activating Token Index: 422