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

Dataset: The Pile

Neuron 1266 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: 0.3965. Min Range: -0.3965

Max Act: 0.3965. Min Act: -0.0000

Data Index: 1509590 (The Pile)

Max Activating Token Index: 172

Text #1

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.3754. Min Act: -0.0000

Data Index: 752043 (The Pile)

Max Activating Token Index: 762

Text #2

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.3852. Min Act: -0.0000

Data Index: 461222 (The Pile)

Max Activating Token Index: 269

Text #3

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.3697. Min Act: -0.0000

Data Index: 950498 (The Pile)

Max Activating Token Index: 1022

Text #4

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.3197. Min Act: -0.0000

Data Index: 1016813 (The Pile)

Max Activating Token Index: 103

Text #5

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.3124. Min Act: -0.0000

Data Index: 820667 (The Pile)

Max Activating Token Index: 28

Text #6

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.3289. Min Act: -0.0000

Data Index: 85701 (The Pile)

Max Activating Token Index: 962

Text #7

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.3238. Min Act: -0.0000

Data Index: 68873 (The Pile)

Max Activating Token Index: 844

Text #8

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.3246. Min Act: -0.0000

Data Index: 1734152 (The Pile)

Max Activating Token Index: 492

Text #9

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2934. Min Act: -0.0000

Data Index: 1421201 (The Pile)

Max Activating Token Index: 120

Text #10

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.3023. Min Act: -0.0000

Data Index: 45332 (The Pile)

Max Activating Token Index: 759

Text #11

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.3074. Min Act: -0.0000

Data Index: 1280120 (The Pile)

Max Activating Token Index: 312

Text #12

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2878. Min Act: -0.0000

Data Index: 396940 (The Pile)

Max Activating Token Index: 122

Text #13

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2734. Min Act: -0.0000

Data Index: 818178 (The Pile)

Max Activating Token Index: 1020

Text #14

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2718. Min Act: -0.0000

Data Index: 1803162 (The Pile)

Max Activating Token Index: 776

Text #15

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2749. Min Act: -0.0000

Data Index: 544845 (The Pile)

Max Activating Token Index: 7

Text #16

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2735. Min Act: -0.0000

Data Index: 874468 (The Pile)

Max Activating Token Index: 859

Text #17

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2684. Min Act: -0.0000

Data Index: 1319449 (The Pile)

Max Activating Token Index: 335

Text #18

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2598. Min Act: -0.0000

Data Index: 478911 (The Pile)

Max Activating Token Index: 452

Text #19

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2577. Min Act: -0.0000

Data Index: 406559 (The Pile)

Max Activating Token Index: 899