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

Dataset: The Pile

Neuron 3403 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: 0.2394. Min Range: -0.2394

Max Act: 0.2394. Min Act: -0.0000

Data Index: 655594 (The Pile)

Max Activating Token Index: 196

Text #1

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.2087. Min Act: -0.0000

Data Index: 1857585 (The Pile)

Max Activating Token Index: 544

Text #2

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.2077. Min Act: -0.0000

Data Index: 1084149 (The Pile)

Max Activating Token Index: 924

Text #3

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1863. Min Act: -0.0000

Data Index: 1859424 (The Pile)

Max Activating Token Index: 650

Text #4

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1951. Min Act: -0.0000

Data Index: 537571 (The Pile)

Max Activating Token Index: 265

Text #5

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1822. Min Act: -0.0000

Data Index: 1589993 (The Pile)

Max Activating Token Index: 316

Text #6

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1565. Min Act: -0.0000

Data Index: 1976809 (The Pile)

Max Activating Token Index: 134

Text #7

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1750. Min Act: -0.0000

Data Index: 848748 (The Pile)

Max Activating Token Index: 46

Text #8

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1685. Min Act: -0.0000

Data Index: 322312 (The Pile)

Max Activating Token Index: 558

Text #9

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1616. Min Act: -0.0000

Data Index: 586 (The Pile)

Max Activating Token Index: 527

Text #10

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1552. Min Act: -0.0000

Data Index: 1004305 (The Pile)

Max Activating Token Index: 349

Text #11

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1546. Min Act: -0.0000

Data Index: 56654 (The Pile)

Max Activating Token Index: 700

Text #12

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1595. Min Act: -0.0000

Data Index: 1914465 (The Pile)

Max Activating Token Index: 52

Text #13

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1529. Min Act: -0.0000

Data Index: 234143 (The Pile)

Max Activating Token Index: 996

Text #14

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1552. Min Act: -0.0000

Data Index: 1952697 (The Pile)

Max Activating Token Index: 335

Text #15

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1442. Min Act: -0.0000

Data Index: 1880250 (The Pile)

Max Activating Token Index: 32

Text #16

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1538. Min Act: -0.0000

Data Index: 1098086 (The Pile)

Max Activating Token Index: 650

Text #17

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1507. Min Act: -0.0000

Data Index: 1670201 (The Pile)

Max Activating Token Index: 101

Text #18

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1419. Min Act: -0.0000

Data Index: 229216 (The Pile)

Max Activating Token Index: 208

Text #19

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1468. Min Act: -0.0000

Data Index: 802601 (The Pile)

Max Activating Token Index: 264