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

Dataset: The Pile

Neuron 2979 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3756. Min Range: -1.3756

Max Act: 1.3219. Min Act: -0.0000

Data Index: 229759 (The Pile)

Max Activating Token Index: 255

Text #1

Max Range: 1.3756. Min Range: -1.3756

Max Act: 1.3756. Min Act: -0.0000

Data Index: 893590 (The Pile)

Max Activating Token Index: 148

Text #2

Max Range: 1.3756. Min Range: -1.3756

Max Act: 1.2168. Min Act: -0.0000

Data Index: 163839 (The Pile)

Max Activating Token Index: 244

Text #3

Max Range: 1.3756. Min Range: -1.3756

Max Act: 1.2040. Min Act: -0.0000

Data Index: 968519 (The Pile)

Max Activating Token Index: 329

Text #4

Max Range: 1.3756. Min Range: -1.3756

Max Act: 1.1887. Min Act: -0.0000

Data Index: 1037054 (The Pile)

Max Activating Token Index: 979

Text #5

Max Range: 1.3756. Min Range: -1.3756

Max Act: 1.1813. Min Act: -0.0000

Data Index: 237450 (The Pile)

Max Activating Token Index: 457

Text #6

Max Range: 1.3756. Min Range: -1.3756

Max Act: 1.1467. Min Act: -0.0000

Data Index: 756985 (The Pile)

Max Activating Token Index: 520

Text #7

Max Range: 1.3756. Min Range: -1.3756

Max Act: 1.1701. Min Act: -0.0000

Data Index: 963302 (The Pile)

Max Activating Token Index: 55

Text #8

Max Range: 1.3756. Min Range: -1.3756

Max Act: 1.0061. Min Act: -0.0000

Data Index: 1888847 (The Pile)

Max Activating Token Index: 233

Text #9

Max Range: 1.3756. Min Range: -1.3756

Max Act: 1.0430. Min Act: -0.0000

Data Index: 1784754 (The Pile)

Max Activating Token Index: 898

Text #10

Max Range: 1.3756. Min Range: -1.3756

Max Act: 1.0739. Min Act: -0.0000

Data Index: 670712 (The Pile)

Max Activating Token Index: 604

Text #11

Max Range: 1.3756. Min Range: -1.3756

Max Act: 1.0614. Min Act: -0.0000

Data Index: 1583530 (The Pile)

Max Activating Token Index: 794

Text #12

Max Range: 1.3756. Min Range: -1.3756

Max Act: 1.0136. Min Act: -0.0000

Data Index: 291301 (The Pile)

Max Activating Token Index: 33

Text #13

Max Range: 1.3756. Min Range: -1.3756

Max Act: 0.9570. Min Act: -0.0000

Data Index: 730046 (The Pile)

Max Activating Token Index: 297

Text #14

Max Range: 1.3756. Min Range: -1.3756

Max Act: 1.0562. Min Act: -0.0000

Data Index: 1842769 (The Pile)

Max Activating Token Index: 878

Text #15

Max Range: 1.3756. Min Range: -1.3756

Max Act: 0.9942. Min Act: -0.0000

Data Index: 290646 (The Pile)

Max Activating Token Index: 125

Text #16

Max Range: 1.3756. Min Range: -1.3756

Max Act: 0.9347. Min Act: -0.0000

Data Index: 1589360 (The Pile)

Max Activating Token Index: 338

Text #17

Max Range: 1.3756. Min Range: -1.3756

Max Act: 0.9553. Min Act: -0.0000

Data Index: 1750700 (The Pile)

Max Activating Token Index: 53

Text #18

Max Range: 1.3756. Min Range: -1.3756

Max Act: 1.0207. Min Act: -0.0000

Data Index: 432918 (The Pile)

Max Activating Token Index: 783

Text #19

Max Range: 1.3756. Min Range: -1.3756

Max Act: 0.9707. Min Act: -0.0000

Data Index: 1104231 (The Pile)

Max Activating Token Index: 551