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

Dataset: The Pile

Neuron 3818 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: 0.9780. Min Range: -0.9780

Max Act: 0.9780. Min Act: -0.0000

Data Index: 1453121 (The Pile)

Max Activating Token Index: 146

Text #1

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.8330. Min Act: -0.0000

Data Index: 159881 (The Pile)

Max Activating Token Index: 503

Text #2

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.8474. Min Act: -0.0000

Data Index: 252550 (The Pile)

Max Activating Token Index: 221

Text #3

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.8429. Min Act: -0.0000

Data Index: 970311 (The Pile)

Max Activating Token Index: 90

Text #4

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.8911. Min Act: -0.0000

Data Index: 1517562 (The Pile)

Max Activating Token Index: 712

Text #5

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.7753. Min Act: -0.0000

Data Index: 1084799 (The Pile)

Max Activating Token Index: 496

Text #6

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.7574. Min Act: -0.0000

Data Index: 557643 (The Pile)

Max Activating Token Index: 419

Text #7

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.7452. Min Act: -0.0000

Data Index: 494605 (The Pile)

Max Activating Token Index: 254

Text #8

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.7355. Min Act: -0.0000

Data Index: 74941 (The Pile)

Max Activating Token Index: 603

Text #9

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.7749. Min Act: -0.0000

Data Index: 554289 (The Pile)

Max Activating Token Index: 970

Text #10

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.7457. Min Act: -0.0000

Data Index: 1054962 (The Pile)

Max Activating Token Index: 248

Text #11

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.7428. Min Act: -0.0000

Data Index: 413868 (The Pile)

Max Activating Token Index: 242

Text #12

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.7235. Min Act: -0.0000

Data Index: 84716 (The Pile)

Max Activating Token Index: 418

Text #13

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.6856. Min Act: -0.0000

Data Index: 1931263 (The Pile)

Max Activating Token Index: 710

Text #14

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.7109. Min Act: -0.0000

Data Index: 1621455 (The Pile)

Max Activating Token Index: 405

Text #15

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.7326. Min Act: -0.0000

Data Index: 1519680 (The Pile)

Max Activating Token Index: 625

Text #16

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.6761. Min Act: -0.0000

Data Index: 1764335 (The Pile)

Max Activating Token Index: 994

Text #17

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.6527. Min Act: -0.0000

Data Index: 1541774 (The Pile)

Max Activating Token Index: 855

Text #18

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.6891. Min Act: -0.0000

Data Index: 1506795 (The Pile)

Max Activating Token Index: 482

Text #19

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.7128. Min Act: 0.0000

Data Index: 955793 (The Pile)

Max Activating Token Index: 931