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

Dataset: The Pile

Neuron 672 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3432. Min Range: -5.3432

Max Act: 5.3432. Min Act: -0.0000

Data Index: 1389422 (The Pile)

Max Activating Token Index: 56

Text #1

Max Range: 5.3432. Min Range: -5.3432

Max Act: 4.6065. Min Act: -0.0000

Data Index: 1660099 (The Pile)

Max Activating Token Index: 45

Text #2

Max Range: 5.3432. Min Range: -5.3432

Max Act: 4.2884. Min Act: -0.0000

Data Index: 1578932 (The Pile)

Max Activating Token Index: 84

Text #3

Max Range: 5.3432. Min Range: -5.3432

Max Act: 4.1620. Min Act: -0.0000

Data Index: 1891709 (The Pile)

Max Activating Token Index: 317

Text #4

Max Range: 5.3432. Min Range: -5.3432

Max Act: 4.2498. Min Act: -0.0000

Data Index: 48708 (The Pile)

Max Activating Token Index: 937

Text #5

Max Range: 5.3432. Min Range: -5.3432

Max Act: 4.1539. Min Act: -0.0000

Data Index: 117248 (The Pile)

Max Activating Token Index: 476

Text #6

Max Range: 5.3432. Min Range: -5.3432

Max Act: 3.9099. Min Act: -0.0000

Data Index: 349888 (The Pile)

Max Activating Token Index: 52

Text #7

Max Range: 5.3432. Min Range: -5.3432

Max Act: 4.0789. Min Act: -0.0000

Data Index: 386651 (The Pile)

Max Activating Token Index: 1019

Text #8

Max Range: 5.3432. Min Range: -5.3432

Max Act: 3.5706. Min Act: -0.0000

Data Index: 1344250 (The Pile)

Max Activating Token Index: 933

Text #9

Max Range: 5.3432. Min Range: -5.3432

Max Act: 3.4726. Min Act: -0.0000

Data Index: 708832 (The Pile)

Max Activating Token Index: 631

Text #10

Max Range: 5.3432. Min Range: -5.3432

Max Act: 3.9278. Min Act: -0.0000

Data Index: 1411762 (The Pile)

Max Activating Token Index: 763

Text #11

Max Range: 5.3432. Min Range: -5.3432

Max Act: 3.7845. Min Act: -0.0000

Data Index: 1622864 (The Pile)

Max Activating Token Index: 1013

Text #12

Max Range: 5.3432. Min Range: -5.3432

Max Act: 3.7100. Min Act: -0.0000

Data Index: 1382545 (The Pile)

Max Activating Token Index: 640

Text #13

Max Range: 5.3432. Min Range: -5.3432

Max Act: 3.0777. Min Act: -0.0000

Data Index: 1237482 (The Pile)

Max Activating Token Index: 889

Text #14

Max Range: 5.3432. Min Range: -5.3432

Max Act: 3.5256. Min Act: -0.0000

Data Index: 1786154 (The Pile)

Max Activating Token Index: 659

Text #15

Max Range: 5.3432. Min Range: -5.3432

Max Act: 3.8271. Min Act: -0.0000

Data Index: 1864693 (The Pile)

Max Activating Token Index: 870

Text #16

Max Range: 5.3432. Min Range: -5.3432

Max Act: 3.7906. Min Act: -0.0000

Data Index: 1868143 (The Pile)

Max Activating Token Index: 903

Text #17

Max Range: 5.3432. Min Range: -5.3432

Max Act: 3.6278. Min Act: -0.0000

Data Index: 528759 (The Pile)

Max Activating Token Index: 33

Text #18

Max Range: 5.3432. Min Range: -5.3432

Max Act: 3.6114. Min Act: -0.0000

Data Index: 1938413 (The Pile)

Max Activating Token Index: 268

Text #19

Max Range: 5.3432. Min Range: -5.3432

Max Act: 3.2697. Min Act: -0.0000

Data Index: 1113205 (The Pile)

Max Activating Token Index: 489