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

Dataset: The Pile

Neuron 4670 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: 1.8819. Min Range: -1.8819

Max Act: 1.8819. Min Act: -0.0000

Data Index: 513145 (The Pile)

Max Activating Token Index: 627

Text #1

Max Range: 1.8819. Min Range: -1.8819

Max Act: 1.8602. Min Act: -0.0000

Data Index: 849367 (The Pile)

Max Activating Token Index: 931

Text #2

Max Range: 1.8819. Min Range: -1.8819

Max Act: 1.6528. Min Act: -0.0000

Data Index: 758955 (The Pile)

Max Activating Token Index: 74

Text #3

Max Range: 1.8819. Min Range: -1.8819

Max Act: 1.4281. Min Act: -0.0000

Data Index: 398689 (The Pile)

Max Activating Token Index: 757

Text #4

Max Range: 1.8819. Min Range: -1.8819

Max Act: 1.4078. Min Act: -0.0000

Data Index: 522605 (The Pile)

Max Activating Token Index: 547

Text #5

Max Range: 1.8819. Min Range: -1.8819

Max Act: 1.2226. Min Act: -0.0000

Data Index: 1261085 (The Pile)

Max Activating Token Index: 511

Text #6

Max Range: 1.8819. Min Range: -1.8819

Max Act: 1.2909. Min Act: -0.0000

Data Index: 898547 (The Pile)

Max Activating Token Index: 647

Text #7

Max Range: 1.8819. Min Range: -1.8819

Max Act: 1.2845. Min Act: -0.0000

Data Index: 121844 (The Pile)

Max Activating Token Index: 197

Text #8

Max Range: 1.8819. Min Range: -1.8819

Max Act: 1.2774. Min Act: -0.0000

Data Index: 1920390 (The Pile)

Max Activating Token Index: 906

Text #9

Max Range: 1.8819. Min Range: -1.8819

Max Act: 1.1938. Min Act: -0.0000

Data Index: 111016 (The Pile)

Max Activating Token Index: 658

Text #10

Max Range: 1.8819. Min Range: -1.8819

Max Act: 1.3375. Min Act: -0.0000

Data Index: 1705676 (The Pile)

Max Activating Token Index: 742

Text #11

Max Range: 1.8819. Min Range: -1.8819

Max Act: 1.2458. Min Act: -0.0000

Data Index: 62347 (The Pile)

Max Activating Token Index: 373

Text #12

Max Range: 1.8819. Min Range: -1.8819

Max Act: 1.1623. Min Act: -0.0000

Data Index: 1341549 (The Pile)

Max Activating Token Index: 105

Text #13

Max Range: 1.8819. Min Range: -1.8819

Max Act: 1.2481. Min Act: -0.0000

Data Index: 363729 (The Pile)

Max Activating Token Index: 280

Text #14

Max Range: 1.8819. Min Range: -1.8819

Max Act: 1.0417. Min Act: -0.0000

Data Index: 414698 (The Pile)

Max Activating Token Index: 74

Text #15

Max Range: 1.8819. Min Range: -1.8819

Max Act: 1.2135. Min Act: -0.0000

Data Index: 900624 (The Pile)

Max Activating Token Index: 866

Text #16

Max Range: 1.8819. Min Range: -1.8819

Max Act: 1.2229. Min Act: -0.0000

Data Index: 1190372 (The Pile)

Max Activating Token Index: 415

Text #17

Max Range: 1.8819. Min Range: -1.8819

Max Act: 1.2819. Min Act: -0.0000

Data Index: 1378224 (The Pile)

Max Activating Token Index: 413

Text #18

Max Range: 1.8819. Min Range: -1.8819

Max Act: 1.2006. Min Act: -0.0000

Data Index: 982657 (The Pile)

Max Activating Token Index: 788

Text #19

Max Range: 1.8819. Min Range: -1.8819

Max Act: 1.1370. Min Act: -0.0000

Data Index: 903027 (The Pile)

Max Activating Token Index: 994