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

Dataset: The Pile

Neuron 100 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: 0.5211. Min Range: -0.5211

Max Act: 0.5211. Min Act: -0.0000

Data Index: 1603916 (The Pile)

Max Activating Token Index: 538

Text #1

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.5139. Min Act: -0.0000

Data Index: 1757571 (The Pile)

Max Activating Token Index: 759

Text #2

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4872. Min Act: -0.0000

Data Index: 641304 (The Pile)

Max Activating Token Index: 321

Text #3

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3923. Min Act: -0.0000

Data Index: 1315114 (The Pile)

Max Activating Token Index: 893

Text #4

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3979. Min Act: -0.0001

Data Index: 258526 (The Pile)

Max Activating Token Index: 1005

Text #5

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3767. Min Act: -0.0000

Data Index: 913800 (The Pile)

Max Activating Token Index: 930

Text #6

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3873. Min Act: -0.0001

Data Index: 1736796 (The Pile)

Max Activating Token Index: 944

Text #7

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4241. Min Act: -0.0000

Data Index: 1013183 (The Pile)

Max Activating Token Index: 21

Text #8

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3825. Min Act: -0.0000

Data Index: 41331 (The Pile)

Max Activating Token Index: 677

Text #9

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3864. Min Act: -0.0000

Data Index: 1010429 (The Pile)

Max Activating Token Index: 115

Text #10

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3918. Min Act: -0.0000

Data Index: 1564012 (The Pile)

Max Activating Token Index: 487

Text #11

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3779. Min Act: -0.0000

Data Index: 1435944 (The Pile)

Max Activating Token Index: 21

Text #12

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3551. Min Act: -0.0000

Data Index: 1095823 (The Pile)

Max Activating Token Index: 805

Text #13

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3663. Min Act: -0.0000

Data Index: 333517 (The Pile)

Max Activating Token Index: 69

Text #14

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3794. Min Act: -0.0000

Data Index: 1389596 (The Pile)

Max Activating Token Index: 450

Text #15

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3507. Min Act: -0.0000

Data Index: 61414 (The Pile)

Max Activating Token Index: 198

Text #16

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3428. Min Act: -0.0000

Data Index: 573250 (The Pile)

Max Activating Token Index: 205

Text #17

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3633. Min Act: -0.0000

Data Index: 792347 (The Pile)

Max Activating Token Index: 488

Text #18

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3549. Min Act: -0.0000

Data Index: 308074 (The Pile)

Max Activating Token Index: 560

Text #19

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3223. Min Act: -0.0000

Data Index: 43837 (The Pile)

Max Activating Token Index: 734