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

Dataset: The Pile

Neuron 4948 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: 3.6493. Min Range: -3.6493

Max Act: 3.6493. Min Act: -0.0000

Data Index: 1296126 (The Pile)

Max Activating Token Index: 64

Text #1

Max Range: 3.6493. Min Range: -3.6493

Max Act: 3.5782. Min Act: -0.0000

Data Index: 1314517 (The Pile)

Max Activating Token Index: 766

Text #2

Max Range: 3.6493. Min Range: -3.6493

Max Act: 3.4853. Min Act: -0.0000

Data Index: 1715330 (The Pile)

Max Activating Token Index: 662

Text #3

Max Range: 3.6493. Min Range: -3.6493

Max Act: 3.3121. Min Act: -0.0000

Data Index: 442980 (The Pile)

Max Activating Token Index: 180

Text #4

Max Range: 3.6493. Min Range: -3.6493

Max Act: 3.4130. Min Act: -0.0000

Data Index: 1293020 (The Pile)

Max Activating Token Index: 380

Text #5

Max Range: 3.6493. Min Range: -3.6493

Max Act: 3.2507. Min Act: -0.0000

Data Index: 133231 (The Pile)

Max Activating Token Index: 300

Text #6

Max Range: 3.6493. Min Range: -3.6493

Max Act: 3.3702. Min Act: -0.0000

Data Index: 669968 (The Pile)

Max Activating Token Index: 743

Text #7

Max Range: 3.6493. Min Range: -3.6493

Max Act: 3.3100. Min Act: -0.0000

Data Index: 1304396 (The Pile)

Max Activating Token Index: 570

Text #8

Max Range: 3.6493. Min Range: -3.6493

Max Act: 3.0707. Min Act: -0.0000

Data Index: 1658947 (The Pile)

Max Activating Token Index: 684

Text #9

Max Range: 3.6493. Min Range: -3.6493

Max Act: 3.1849. Min Act: -0.0000

Data Index: 379455 (The Pile)

Max Activating Token Index: 785

Text #10

Max Range: 3.6493. Min Range: -3.6493

Max Act: 2.9623. Min Act: -0.0000

Data Index: 1100718 (The Pile)

Max Activating Token Index: 67

Text #11

Max Range: 3.6493. Min Range: -3.6493

Max Act: 3.2287. Min Act: -0.0000

Data Index: 600767 (The Pile)

Max Activating Token Index: 611

Text #12

Max Range: 3.6493. Min Range: -3.6493

Max Act: 3.2211. Min Act: -0.0000

Data Index: 1035849 (The Pile)

Max Activating Token Index: 60

Text #13

Max Range: 3.6493. Min Range: -3.6493

Max Act: 3.2130. Min Act: -0.0000

Data Index: 696499 (The Pile)

Max Activating Token Index: 23

Text #14

Max Range: 3.6493. Min Range: -3.6493

Max Act: 3.0548. Min Act: -0.0000

Data Index: 234617 (The Pile)

Max Activating Token Index: 466

Text #15

Max Range: 3.6493. Min Range: -3.6493

Max Act: 3.5152. Min Act: -0.0000

Data Index: 1440585 (The Pile)

Max Activating Token Index: 807

Text #16

Max Range: 3.6493. Min Range: -3.6493

Max Act: 3.1685. Min Act: -0.0000

Data Index: 1995646 (The Pile)

Max Activating Token Index: 659

Text #17

Max Range: 3.6493. Min Range: -3.6493

Max Act: 3.1338. Min Act: -0.0000

Data Index: 1095858 (The Pile)

Max Activating Token Index: 47

Text #18

Max Range: 3.6493. Min Range: -3.6493

Max Act: 3.3128. Min Act: -0.0000

Data Index: 819633 (The Pile)

Max Activating Token Index: 363

Text #19

Max Range: 3.6493. Min Range: -3.6493

Max Act: 3.1097. Min Act: -0.0000

Data Index: 1290681 (The Pile)

Max Activating Token Index: 223