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

Dataset: The Pile

Neuron 2999 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: 0.9925. Min Range: -0.9925

Max Act: 0.9925. Min Act: -0.0000

Data Index: 1095736 (The Pile)

Max Activating Token Index: 294

Text #1

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.8752. Min Act: -0.0000

Data Index: 948549 (The Pile)

Max Activating Token Index: 637

Text #2

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.9872. Min Act: -0.0000

Data Index: 729854 (The Pile)

Max Activating Token Index: 787

Text #3

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.7992. Min Act: -0.0000

Data Index: 306033 (The Pile)

Max Activating Token Index: 452

Text #4

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.8510. Min Act: -0.0000

Data Index: 1610686 (The Pile)

Max Activating Token Index: 991

Text #5

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.7562. Min Act: -0.0000

Data Index: 984660 (The Pile)

Max Activating Token Index: 574

Text #6

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.7725. Min Act: -0.0000

Data Index: 1004688 (The Pile)

Max Activating Token Index: 229

Text #7

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.7661. Min Act: -0.0000

Data Index: 1229750 (The Pile)

Max Activating Token Index: 949

Text #8

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.6967. Min Act: -0.0000

Data Index: 850437 (The Pile)

Max Activating Token Index: 702

Text #9

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.7445. Min Act: -0.0000

Data Index: 436018 (The Pile)

Max Activating Token Index: 772

Text #10

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.6957. Min Act: -0.0000

Data Index: 1483473 (The Pile)

Max Activating Token Index: 317

Text #11

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.7094. Min Act: -0.0000

Data Index: 913638 (The Pile)

Max Activating Token Index: 851

Text #12

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.6843. Min Act: -0.0000

Data Index: 665178 (The Pile)

Max Activating Token Index: 493

Text #13

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.6737. Min Act: -0.0000

Data Index: 381762 (The Pile)

Max Activating Token Index: 409

Text #14

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.6330. Min Act: -0.0000

Data Index: 1434226 (The Pile)

Max Activating Token Index: 344

Text #15

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.6633. Min Act: -0.0000

Data Index: 888569 (The Pile)

Max Activating Token Index: 488

Text #16

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.5925. Min Act: -0.0000

Data Index: 663750 (The Pile)

Max Activating Token Index: 1010

Text #17

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.6260. Min Act: -0.0000

Data Index: 622574 (The Pile)

Max Activating Token Index: 350

Text #18

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.6686. Min Act: -0.0000

Data Index: 1318252 (The Pile)

Max Activating Token Index: 937

Text #19

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.6516. Min Act: -0.0000

Data Index: 1998094 (The Pile)

Max Activating Token Index: 1018