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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3613 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 6.2948. Min Range: -6.2948

Max Act: 6.2948. Min Act: -0.0000

Data Index: 1380086 (Python Code)

Max Activating Token Index: 793

Text #1

Max Range: 6.2948. Min Range: -6.2948

Max Act: 5.9609. Min Act: -0.0000

Data Index: 1419933 (Python Code)

Max Activating Token Index: 685

Text #2

Max Range: 6.2948. Min Range: -6.2948

Max Act: 5.8740. Min Act: -0.0000

Data Index: 1605476 (Python Code)

Max Activating Token Index: 148

Text #3

Max Range: 6.2948. Min Range: -6.2948

Max Act: 5.9875. Min Act: -0.0000

Data Index: 1636317 (Python Code)

Max Activating Token Index: 715

Text #4

Max Range: 6.2948. Min Range: -6.2948

Max Act: 5.8157. Min Act: -0.0000

Data Index: 1544428 (Python Code)

Max Activating Token Index: 133

Text #5

Max Range: 6.2948. Min Range: -6.2948

Max Act: 5.7635. Min Act: -0.0000

Data Index: 1449490 (Python Code)

Max Activating Token Index: 869

Text #6

Max Range: 6.2948. Min Range: -6.2948

Max Act: 5.7683. Min Act: -0.0000

Data Index: 1583854 (Python Code)

Max Activating Token Index: 82

Text #7

Max Range: 6.2948. Min Range: -6.2948

Max Act: 5.5199. Min Act: -0.0000

Data Index: 1639852 (Python Code)

Max Activating Token Index: 214

Text #8

Max Range: 6.2948. Min Range: -6.2948

Max Act: 5.5220. Min Act: -0.0000

Data Index: 1493624 (Python Code)

Max Activating Token Index: 241

Text #9

Max Range: 6.2948. Min Range: -6.2948

Max Act: 5.6631. Min Act: -0.0000

Data Index: 1613439 (Python Code)

Max Activating Token Index: 806

Text #10

Max Range: 6.2948. Min Range: -6.2948

Max Act: 5.6783. Min Act: -0.0000

Data Index: 1395260 (Python Code)

Max Activating Token Index: 653

Text #11

Max Range: 6.2948. Min Range: -6.2948

Max Act: 5.6367. Min Act: -0.0000

Data Index: 1545913 (Python Code)

Max Activating Token Index: 978

Text #12

Max Range: 6.2948. Min Range: -6.2948

Max Act: 5.8025. Min Act: -0.0000

Data Index: 1433291 (Python Code)

Max Activating Token Index: 950

Text #13

Max Range: 6.2948. Min Range: -6.2948

Max Act: 5.4485. Min Act: -0.0000

Data Index: 1488613 (Python Code)

Max Activating Token Index: 478

Text #14

Max Range: 6.2948. Min Range: -6.2948

Max Act: 5.5836. Min Act: -0.0000

Data Index: 1436665 (Python Code)

Max Activating Token Index: 978

Text #15

Max Range: 6.2948. Min Range: -6.2948

Max Act: 5.7519. Min Act: -0.0000

Data Index: 1480766 (Python Code)

Max Activating Token Index: 232

Text #16

Max Range: 6.2948. Min Range: -6.2948

Max Act: 5.5778. Min Act: -0.0000

Data Index: 1484418 (Python Code)

Max Activating Token Index: 982

Text #17

Max Range: 6.2948. Min Range: -6.2948

Max Act: 5.5281. Min Act: -0.0000

Data Index: 1516108 (Python Code)

Max Activating Token Index: 578

Text #18

Max Range: 6.2948. Min Range: -6.2948

Max Act: 5.4986. Min Act: -0.0000

Data Index: 1391830 (Python Code)

Max Activating Token Index: 847

Text #19

Max Range: 6.2948. Min Range: -6.2948

Max Act: 5.4925. Min Act: -0.0000

Data Index: 1579519 (Python Code)

Max Activating Token Index: 88