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

Dataset: The Pile

Neuron 320 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6355. Min Range: -4.6355

Max Act: 4.6355. Min Act: -0.0000

Data Index: 1819012 (The Pile)

Max Activating Token Index: 512

Text #1

Max Range: 4.6355. Min Range: -4.6355

Max Act: 4.0475. Min Act: -0.0000

Data Index: 1887830 (The Pile)

Max Activating Token Index: 890

Text #2

Max Range: 4.6355. Min Range: -4.6355

Max Act: 3.8157. Min Act: -0.0000

Data Index: 1490704 (The Pile)

Max Activating Token Index: 747

Text #3

Max Range: 4.6355. Min Range: -4.6355

Max Act: 3.6635. Min Act: -0.0000

Data Index: 1893400 (The Pile)

Max Activating Token Index: 911

Text #4

Max Range: 4.6355. Min Range: -4.6355

Max Act: 3.4421. Min Act: -0.0000

Data Index: 999508 (The Pile)

Max Activating Token Index: 726

Text #5

Max Range: 4.6355. Min Range: -4.6355

Max Act: 3.7332. Min Act: -0.0000

Data Index: 572963 (The Pile)

Max Activating Token Index: 847

Text #6

Max Range: 4.6355. Min Range: -4.6355

Max Act: 3.2551. Min Act: -0.0000

Data Index: 590791 (The Pile)

Max Activating Token Index: 663

Text #7

Max Range: 4.6355. Min Range: -4.6355

Max Act: 3.5393. Min Act: -0.0000

Data Index: 347198 (The Pile)

Max Activating Token Index: 291

Text #8

Max Range: 4.6355. Min Range: -4.6355

Max Act: 3.4852. Min Act: -0.0000

Data Index: 1715128 (The Pile)

Max Activating Token Index: 594

Text #9

Max Range: 4.6355. Min Range: -4.6355

Max Act: 3.6498. Min Act: -0.0000

Data Index: 1403630 (The Pile)

Max Activating Token Index: 688

Text #10

Max Range: 4.6355. Min Range: -4.6355

Max Act: 3.4575. Min Act: -0.0000

Data Index: 1121935 (The Pile)

Max Activating Token Index: 420

Text #11

Max Range: 4.6355. Min Range: -4.6355

Max Act: 3.7632. Min Act: -0.0000

Data Index: 1669312 (The Pile)

Max Activating Token Index: 936

Text #12

Max Range: 4.6355. Min Range: -4.6355

Max Act: 3.6086. Min Act: -0.0000

Data Index: 1141198 (The Pile)

Max Activating Token Index: 402

Text #13

Max Range: 4.6355. Min Range: -4.6355

Max Act: 3.2939. Min Act: -0.0000

Data Index: 984457 (The Pile)

Max Activating Token Index: 691

Text #14

Max Range: 4.6355. Min Range: -4.6355

Max Act: 3.3975. Min Act: -0.0000

Data Index: 53271 (The Pile)

Max Activating Token Index: 667

Text #15

Max Range: 4.6355. Min Range: -4.6355

Max Act: 3.2424. Min Act: -0.0000

Data Index: 752626 (The Pile)

Max Activating Token Index: 852

Text #16

Max Range: 4.6355. Min Range: -4.6355

Max Act: 3.6671. Min Act: -0.0000

Data Index: 288005 (The Pile)

Max Activating Token Index: 863

Text #17

Max Range: 4.6355. Min Range: -4.6355

Max Act: 3.3316. Min Act: -0.0000

Data Index: 1833503 (The Pile)

Max Activating Token Index: 205

Text #18

Max Range: 4.6355. Min Range: -4.6355

Max Act: 3.3293. Min Act: -0.0000

Data Index: 1115792 (The Pile)

Max Activating Token Index: 743

Text #19

Max Range: 4.6355. Min Range: -4.6355

Max Act: 3.4802. Min Act: -0.0000

Data Index: 1451362 (The Pile)

Max Activating Token Index: 704