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

Dataset: The Pile

Neuron 4562 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: 3.4519. Min Range: -3.4519

Max Act: 3.4519. Min Act: -0.0000

Data Index: 1499335 (The Pile)

Max Activating Token Index: 862

Text #1

Max Range: 3.4519. Min Range: -3.4519

Max Act: 3.1335. Min Act: -0.0000

Data Index: 777512 (The Pile)

Max Activating Token Index: 12

Text #2

Max Range: 3.4519. Min Range: -3.4519

Max Act: 2.7535. Min Act: -0.0000

Data Index: 1518413 (The Pile)

Max Activating Token Index: 864

Text #3

Max Range: 3.4519. Min Range: -3.4519

Max Act: 2.5618. Min Act: -0.0000

Data Index: 623384 (The Pile)

Max Activating Token Index: 970

Text #4

Max Range: 3.4519. Min Range: -3.4519

Max Act: 2.6804. Min Act: -0.0000

Data Index: 620278 (The Pile)

Max Activating Token Index: 390

Text #5

Max Range: 3.4519. Min Range: -3.4519

Max Act: 2.5604. Min Act: -0.0000

Data Index: 1056777 (The Pile)

Max Activating Token Index: 611

Text #6

Max Range: 3.4519. Min Range: -3.4519

Max Act: 2.4603. Min Act: -0.0000

Data Index: 902864 (The Pile)

Max Activating Token Index: 12

Text #7

Max Range: 3.4519. Min Range: -3.4519

Max Act: 2.3934. Min Act: -0.0000

Data Index: 1591881 (The Pile)

Max Activating Token Index: 484

Text #8

Max Range: 3.4519. Min Range: -3.4519

Max Act: 2.2609. Min Act: -0.0000

Data Index: 256589 (The Pile)

Max Activating Token Index: 150

Text #9

Max Range: 3.4519. Min Range: -3.4519

Max Act: 1.9400. Min Act: -0.0000

Data Index: 381663 (The Pile)

Max Activating Token Index: 721

Text #10

Max Range: 3.4519. Min Range: -3.4519

Max Act: 2.3105. Min Act: -0.0000

Data Index: 1817636 (The Pile)

Max Activating Token Index: 109

Text #11

Max Range: 3.4519. Min Range: -3.4519

Max Act: 2.3063. Min Act: -0.0000

Data Index: 1638411 (The Pile)

Max Activating Token Index: 55

Text #12

Max Range: 3.4519. Min Range: -3.4519

Max Act: 2.2929. Min Act: -0.0000

Data Index: 39834 (The Pile)

Max Activating Token Index: 819

Text #13

Max Range: 3.4519. Min Range: -3.4519

Max Act: 2.1896. Min Act: -0.0000

Data Index: 1424770 (The Pile)

Max Activating Token Index: 707

Text #14

Max Range: 3.4519. Min Range: -3.4519

Max Act: 2.3346. Min Act: -0.0000

Data Index: 365286 (The Pile)

Max Activating Token Index: 27

Text #15

Max Range: 3.4519. Min Range: -3.4519

Max Act: 2.1626. Min Act: -0.0000

Data Index: 1814302 (The Pile)

Max Activating Token Index: 610

Text #16

Max Range: 3.4519. Min Range: -3.4519

Max Act: 2.3989. Min Act: -0.0000

Data Index: 1652909 (The Pile)

Max Activating Token Index: 29

Text #17

Max Range: 3.4519. Min Range: -3.4519

Max Act: 2.1319. Min Act: -0.0000

Data Index: 266087 (The Pile)

Max Activating Token Index: 189

Text #18

Max Range: 3.4519. Min Range: -3.4519

Max Act: 2.1012. Min Act: -0.0000

Data Index: 310601 (The Pile)

Max Activating Token Index: 199

Text #19

Max Range: 3.4519. Min Range: -3.4519

Max Act: 2.2161. Min Act: -0.0000

Data Index: 368209 (The Pile)

Max Activating Token Index: 249