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

Dataset: The Pile

Neuron 2651 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: 1.5240. Min Range: -1.5240

Max Act: 1.5240. Min Act: -0.0000

Data Index: 1684405 (The Pile)

Max Activating Token Index: 769

Text #1

Max Range: 1.5240. Min Range: -1.5240

Max Act: 1.2828. Min Act: -0.0000

Data Index: 1990550 (The Pile)

Max Activating Token Index: 383

Text #2

Max Range: 1.5240. Min Range: -1.5240

Max Act: 1.4499. Min Act: -0.0000

Data Index: 1269360 (The Pile)

Max Activating Token Index: 155

Text #3

Max Range: 1.5240. Min Range: -1.5240

Max Act: 1.2156. Min Act: -0.0000

Data Index: 965874 (The Pile)

Max Activating Token Index: 127

Text #4

Max Range: 1.5240. Min Range: -1.5240

Max Act: 1.1022. Min Act: -0.0000

Data Index: 1229691 (The Pile)

Max Activating Token Index: 687

Text #5

Max Range: 1.5240. Min Range: -1.5240

Max Act: 1.1989. Min Act: -0.0000

Data Index: 224010 (The Pile)

Max Activating Token Index: 655

Text #6

Max Range: 1.5240. Min Range: -1.5240

Max Act: 1.0461. Min Act: -0.0000

Data Index: 744267 (The Pile)

Max Activating Token Index: 538

Text #7

Max Range: 1.5240. Min Range: -1.5240

Max Act: 1.1865. Min Act: -0.0000

Data Index: 596152 (The Pile)

Max Activating Token Index: 870

Text #8

Max Range: 1.5240. Min Range: -1.5240

Max Act: 1.1164. Min Act: -0.0000

Data Index: 332194 (The Pile)

Max Activating Token Index: 592

Text #9

Max Range: 1.5240. Min Range: -1.5240

Max Act: 1.1921. Min Act: -0.0000

Data Index: 1383002 (The Pile)

Max Activating Token Index: 486

Text #10

Max Range: 1.5240. Min Range: -1.5240

Max Act: 1.0445. Min Act: -0.0000

Data Index: 1611596 (The Pile)

Max Activating Token Index: 296

Text #11

Max Range: 1.5240. Min Range: -1.5240

Max Act: 1.1025. Min Act: -0.0000

Data Index: 1770633 (The Pile)

Max Activating Token Index: 408

Text #12

Max Range: 1.5240. Min Range: -1.5240

Max Act: 1.0004. Min Act: -0.0000

Data Index: 1421658 (The Pile)

Max Activating Token Index: 743

Text #13

Max Range: 1.5240. Min Range: -1.5240

Max Act: 1.0986. Min Act: -0.0000

Data Index: 893039 (The Pile)

Max Activating Token Index: 675

Text #14

Max Range: 1.5240. Min Range: -1.5240

Max Act: 0.7902. Min Act: -0.0000

Data Index: 1267057 (The Pile)

Max Activating Token Index: 507

Text #15

Max Range: 1.5240. Min Range: -1.5240

Max Act: 1.1535. Min Act: 0.0000

Data Index: 1430533 (The Pile)

Max Activating Token Index: 275

Text #16

Max Range: 1.5240. Min Range: -1.5240

Max Act: 1.1270. Min Act: -0.0000

Data Index: 1713873 (The Pile)

Max Activating Token Index: 203

Text #17

Max Range: 1.5240. Min Range: -1.5240

Max Act: 1.0427. Min Act: -0.0001

Data Index: 276119 (The Pile)

Max Activating Token Index: 711

Text #18

Max Range: 1.5240. Min Range: -1.5240

Max Act: 1.0042. Min Act: -0.0000

Data Index: 1027988 (The Pile)

Max Activating Token Index: 411

Text #19

Max Range: 1.5240. Min Range: -1.5240

Max Act: 1.0871. Min Act: -0.0000

Data Index: 1156124 (The Pile)

Max Activating Token Index: 126