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

Dataset: The Pile

Neuron 4087 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4436. Min Range: -1.4436

Max Act: 1.4436. Min Act: -0.0000

Data Index: 583184 (The Pile)

Max Activating Token Index: 647

Text #1

Max Range: 1.4436. Min Range: -1.4436

Max Act: 1.1737. Min Act: -0.0000

Data Index: 519029 (The Pile)

Max Activating Token Index: 1017

Text #2

Max Range: 1.4436. Min Range: -1.4436

Max Act: 1.1715. Min Act: -0.0000

Data Index: 123692 (The Pile)

Max Activating Token Index: 1018

Text #3

Max Range: 1.4436. Min Range: -1.4436

Max Act: 1.0430. Min Act: -0.0000

Data Index: 1667900 (The Pile)

Max Activating Token Index: 983

Text #4

Max Range: 1.4436. Min Range: -1.4436

Max Act: 1.0273. Min Act: -0.0000

Data Index: 248043 (The Pile)

Max Activating Token Index: 869

Text #5

Max Range: 1.4436. Min Range: -1.4436

Max Act: 1.0877. Min Act: -0.0000

Data Index: 677393 (The Pile)

Max Activating Token Index: 917

Text #6

Max Range: 1.4436. Min Range: -1.4436

Max Act: 1.0370. Min Act: -0.0000

Data Index: 641028 (The Pile)

Max Activating Token Index: 982

Text #7

Max Range: 1.4436. Min Range: -1.4436

Max Act: 1.0182. Min Act: -0.0000

Data Index: 1624230 (The Pile)

Max Activating Token Index: 156

Text #8

Max Range: 1.4436. Min Range: -1.4436

Max Act: 1.0755. Min Act: -0.0000

Data Index: 297802 (The Pile)

Max Activating Token Index: 643

Text #9

Max Range: 1.4436. Min Range: -1.4436

Max Act: 1.0465. Min Act: -0.0000

Data Index: 1539075 (The Pile)

Max Activating Token Index: 556

Text #10

Max Range: 1.4436. Min Range: -1.4436

Max Act: 1.0115. Min Act: -0.0000

Data Index: 154038 (The Pile)

Max Activating Token Index: 817

Text #11

Max Range: 1.4436. Min Range: -1.4436

Max Act: 0.9831. Min Act: -0.0000

Data Index: 1084383 (The Pile)

Max Activating Token Index: 584

Text #12

Max Range: 1.4436. Min Range: -1.4436

Max Act: 0.9952. Min Act: -0.0000

Data Index: 1435560 (The Pile)

Max Activating Token Index: 999

Text #13

Max Range: 1.4436. Min Range: -1.4436

Max Act: 0.9342. Min Act: -0.0000

Data Index: 605885 (The Pile)

Max Activating Token Index: 798

Text #14

Max Range: 1.4436. Min Range: -1.4436

Max Act: 0.9700. Min Act: -0.0000

Data Index: 1501969 (The Pile)

Max Activating Token Index: 552

Text #15

Max Range: 1.4436. Min Range: -1.4436

Max Act: 1.0525. Min Act: -0.0000

Data Index: 771876 (The Pile)

Max Activating Token Index: 205

Text #16

Max Range: 1.4436. Min Range: -1.4436

Max Act: 0.9952. Min Act: -0.0000

Data Index: 1441171 (The Pile)

Max Activating Token Index: 846

Text #17

Max Range: 1.4436. Min Range: -1.4436

Max Act: 0.9632. Min Act: -0.0000

Data Index: 1453555 (The Pile)

Max Activating Token Index: 805

Text #18

Max Range: 1.4436. Min Range: -1.4436

Max Act: 1.0524. Min Act: -0.0000

Data Index: 1737892 (The Pile)

Max Activating Token Index: 234

Text #19

Max Range: 1.4436. Min Range: -1.4436

Max Act: 1.0206. Min Act: -0.0000

Data Index: 459769 (The Pile)

Max Activating Token Index: 961