Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1735 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.4201. Min Act: -0.0000

Data Index: 842441 (The Pile)

Max Activating Token Index: 1012

Text #1

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.4086. Min Act: -0.0000

Data Index: 1479198 (The Pile)

Max Activating Token Index: 20

Text #2

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.3557. Min Act: -0.0000

Data Index: 820147 (The Pile)

Max Activating Token Index: 913

Text #3

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.3329. Min Act: -0.0000

Data Index: 951489 (The Pile)

Max Activating Token Index: 960

Text #4

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.3092. Min Act: -0.0000

Data Index: 1618810 (The Pile)

Max Activating Token Index: 257

Text #5

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.3109. Min Act: -0.0000

Data Index: 696924 (The Pile)

Max Activating Token Index: 246

Text #6

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.2951. Min Act: -0.0000

Data Index: 1560495 (The Pile)

Max Activating Token Index: 613

Text #7

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.2823. Min Act: -0.0000

Data Index: 1480585 (The Pile)

Max Activating Token Index: 756

Text #8

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.2800. Min Act: -0.0000

Data Index: 1151709 (The Pile)

Max Activating Token Index: 638

Text #9

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.2787. Min Act: -0.0000

Data Index: 658810 (The Pile)

Max Activating Token Index: 212

Text #10

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.2824. Min Act: -0.0000

Data Index: 1699918 (The Pile)

Max Activating Token Index: 185

Text #11

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.2729. Min Act: -0.0000

Data Index: 1335333 (The Pile)

Max Activating Token Index: 949

Text #12

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.2837. Min Act: -0.0000

Data Index: 390595 (The Pile)

Max Activating Token Index: 920

Text #13

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.2702. Min Act: -0.0000

Data Index: 1225627 (The Pile)

Max Activating Token Index: 890

Text #14

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.2519. Min Act: -0.0001

Data Index: 720681 (The Pile)

Max Activating Token Index: 647

Text #15

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.2695. Min Act: -0.0000

Data Index: 788715 (The Pile)

Max Activating Token Index: 461

Text #16

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.2787. Min Act: -0.0000

Data Index: 1671905 (The Pile)

Max Activating Token Index: 668

Text #17

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.2599. Min Act: -0.0000

Data Index: 1021028 (The Pile)

Max Activating Token Index: 76

Text #18

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.2658. Min Act: -0.0000

Data Index: 1081370 (The Pile)

Max Activating Token Index: 240

Text #19

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.2743. Min Act: -0.0000

Data Index: 107497 (The Pile)

Max Activating Token Index: 318