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

Dataset: The Pile

Neuron 2296 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.9886. Min Range: -8.9886

Max Act: 8.6853. Min Act: -0.0000

Data Index: 1569355 (The Pile)

Max Activating Token Index: 842

Text #1

Max Range: 8.9886. Min Range: -8.9886

Max Act: 8.3318. Min Act: -0.0000

Data Index: 694153 (The Pile)

Max Activating Token Index: 183

Text #2

Max Range: 8.9886. Min Range: -8.9886

Max Act: 8.9886. Min Act: -0.0000

Data Index: 1581929 (The Pile)

Max Activating Token Index: 976

Text #3

Max Range: 8.9886. Min Range: -8.9886

Max Act: 8.6248. Min Act: -0.0000

Data Index: 1109961 (The Pile)

Max Activating Token Index: 405

Text #4

Max Range: 8.9886. Min Range: -8.9886

Max Act: 8.1471. Min Act: -0.0000

Data Index: 1460155 (The Pile)

Max Activating Token Index: 946

Text #5

Max Range: 8.9886. Min Range: -8.9886

Max Act: 8.9108. Min Act: -0.0000

Data Index: 386564 (The Pile)

Max Activating Token Index: 975

Text #6

Max Range: 8.9886. Min Range: -8.9886

Max Act: 8.9662. Min Act: -0.0000

Data Index: 1438906 (The Pile)

Max Activating Token Index: 840

Text #7

Max Range: 8.9886. Min Range: -8.9886

Max Act: 8.5416. Min Act: -0.0000

Data Index: 1583506 (The Pile)

Max Activating Token Index: 357

Text #8

Max Range: 8.9886. Min Range: -8.9886

Max Act: 8.3545. Min Act: -0.0000

Data Index: 463164 (The Pile)

Max Activating Token Index: 983

Text #9

Max Range: 8.9886. Min Range: -8.9886

Max Act: 8.2494. Min Act: -0.0000

Data Index: 1976021 (The Pile)

Max Activating Token Index: 896

Text #10

Max Range: 8.9886. Min Range: -8.9886

Max Act: 7.9516. Min Act: -0.0000

Data Index: 299797 (The Pile)

Max Activating Token Index: 868

Text #11

Max Range: 8.9886. Min Range: -8.9886

Max Act: 8.1269. Min Act: -0.0000

Data Index: 698032 (The Pile)

Max Activating Token Index: 869

Text #12

Max Range: 8.9886. Min Range: -8.9886

Max Act: 8.0011. Min Act: -0.0000

Data Index: 642659 (The Pile)

Max Activating Token Index: 397

Text #13

Max Range: 8.9886. Min Range: -8.9886

Max Act: 7.3107. Min Act: -0.0000

Data Index: 1716024 (The Pile)

Max Activating Token Index: 980

Text #14

Max Range: 8.9886. Min Range: -8.9886

Max Act: 7.4638. Min Act: -0.0000

Data Index: 35488 (The Pile)

Max Activating Token Index: 333

Text #15

Max Range: 8.9886. Min Range: -8.9886

Max Act: 8.0494. Min Act: -0.0000

Data Index: 190121 (The Pile)

Max Activating Token Index: 751

Text #16

Max Range: 8.9886. Min Range: -8.9886

Max Act: 7.3472. Min Act: -0.0000

Data Index: 520028 (The Pile)

Max Activating Token Index: 409

Text #17

Max Range: 8.9886. Min Range: -8.9886

Max Act: 7.3445. Min Act: -0.0000

Data Index: 1876607 (The Pile)

Max Activating Token Index: 438

Text #18

Max Range: 8.9886. Min Range: -8.9886

Max Act: 7.0544. Min Act: -0.0000

Data Index: 856885 (The Pile)

Max Activating Token Index: 438

Text #19

Max Range: 8.9886. Min Range: -8.9886

Max Act: 7.2045. Min Act: -0.0000

Data Index: 1746586 (The Pile)

Max Activating Token Index: 134