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

Dataset: The Pile

Neuron 1415 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: 0.7585. Min Range: -0.7585

Max Act: 0.7457. Min Act: -0.0000

Data Index: 1111664 (The Pile)

Max Activating Token Index: 752

Text #1

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.7585. Min Act: -0.0000

Data Index: 537869 (The Pile)

Max Activating Token Index: 764

Text #2

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.7173. Min Act: -0.0000

Data Index: 747187 (The Pile)

Max Activating Token Index: 989

Text #3

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.7133. Min Act: -0.0000

Data Index: 1409393 (The Pile)

Max Activating Token Index: 896

Text #4

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6591. Min Act: -0.0000

Data Index: 725917 (The Pile)

Max Activating Token Index: 919

Text #5

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6757. Min Act: -0.0000

Data Index: 1462452 (The Pile)

Max Activating Token Index: 81

Text #6

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6849. Min Act: -0.0000

Data Index: 1410034 (The Pile)

Max Activating Token Index: 627

Text #7

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6407. Min Act: -0.0000

Data Index: 723843 (The Pile)

Max Activating Token Index: 887

Text #8

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6585. Min Act: -0.0000

Data Index: 1828614 (The Pile)

Max Activating Token Index: 418

Text #9

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6539. Min Act: -0.0000

Data Index: 1336391 (The Pile)

Max Activating Token Index: 951

Text #10

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6086. Min Act: -0.0000

Data Index: 466650 (The Pile)

Max Activating Token Index: 479

Text #11

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6772. Min Act: -0.0000

Data Index: 1972059 (The Pile)

Max Activating Token Index: 997

Text #12

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6273. Min Act: -0.0000

Data Index: 1646583 (The Pile)

Max Activating Token Index: 449

Text #13

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6213. Min Act: -0.0000

Data Index: 1980688 (The Pile)

Max Activating Token Index: 537

Text #14

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6015. Min Act: -0.0000

Data Index: 319086 (The Pile)

Max Activating Token Index: 260

Text #15

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.5972. Min Act: -0.0000

Data Index: 176672 (The Pile)

Max Activating Token Index: 245

Text #16

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6431. Min Act: -0.0000

Data Index: 1743259 (The Pile)

Max Activating Token Index: 989

Text #17

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6164. Min Act: -0.0000

Data Index: 520228 (The Pile)

Max Activating Token Index: 660

Text #18

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6123. Min Act: -0.0000

Data Index: 236191 (The Pile)

Max Activating Token Index: 578

Text #19

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6210. Min Act: -0.0000

Data Index: 512533 (The Pile)

Max Activating Token Index: 772