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

Dataset: The Pile

Neuron 3408 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: 1.4419. Min Range: -1.4419

Max Act: 1.4419. Min Act: -0.0000

Data Index: 1387546 (The Pile)

Max Activating Token Index: 25

Text #1

Max Range: 1.4419. Min Range: -1.4419

Max Act: 1.0207. Min Act: -0.0000

Data Index: 250502 (The Pile)

Max Activating Token Index: 43

Text #2

Max Range: 1.4419. Min Range: -1.4419

Max Act: 1.0010. Min Act: -0.0000

Data Index: 1059832 (The Pile)

Max Activating Token Index: 338

Text #3

Max Range: 1.4419. Min Range: -1.4419

Max Act: 1.0067. Min Act: -0.0000

Data Index: 585786 (The Pile)

Max Activating Token Index: 469

Text #4

Max Range: 1.4419. Min Range: -1.4419

Max Act: 0.9455. Min Act: -0.0000

Data Index: 1461439 (The Pile)

Max Activating Token Index: 337

Text #5

Max Range: 1.4419. Min Range: -1.4419

Max Act: 0.9805. Min Act: -0.0000

Data Index: 263579 (The Pile)

Max Activating Token Index: 594

Text #6

Max Range: 1.4419. Min Range: -1.4419

Max Act: 0.9434. Min Act: -0.0000

Data Index: 899076 (The Pile)

Max Activating Token Index: 239

Text #7

Max Range: 1.4419. Min Range: -1.4419

Max Act: 0.8811. Min Act: -0.0000

Data Index: 1852868 (The Pile)

Max Activating Token Index: 307

Text #8

Max Range: 1.4419. Min Range: -1.4419

Max Act: 0.9304. Min Act: -0.0000

Data Index: 1684883 (The Pile)

Max Activating Token Index: 729

Text #9

Max Range: 1.4419. Min Range: -1.4419

Max Act: 0.8744. Min Act: -0.0000

Data Index: 1330425 (The Pile)

Max Activating Token Index: 99

Text #10

Max Range: 1.4419. Min Range: -1.4419

Max Act: 0.9281. Min Act: -0.0000

Data Index: 887991 (The Pile)

Max Activating Token Index: 420

Text #11

Max Range: 1.4419. Min Range: -1.4419

Max Act: 0.8743. Min Act: -0.0000

Data Index: 123173 (The Pile)

Max Activating Token Index: 39

Text #12

Max Range: 1.4419. Min Range: -1.4419

Max Act: 0.8631. Min Act: -0.0000

Data Index: 911039 (The Pile)

Max Activating Token Index: 122

Text #13

Max Range: 1.4419. Min Range: -1.4419

Max Act: 0.8883. Min Act: -0.0000

Data Index: 188315 (The Pile)

Max Activating Token Index: 30

Text #14

Max Range: 1.4419. Min Range: -1.4419

Max Act: 0.8526. Min Act: -0.0000

Data Index: 623712 (The Pile)

Max Activating Token Index: 631

Text #15

Max Range: 1.4419. Min Range: -1.4419

Max Act: 0.8011. Min Act: -0.0000

Data Index: 1257628 (The Pile)

Max Activating Token Index: 733

Text #16

Max Range: 1.4419. Min Range: -1.4419

Max Act: 0.8243. Min Act: -0.0000

Data Index: 796569 (The Pile)

Max Activating Token Index: 117

Text #17

Max Range: 1.4419. Min Range: -1.4419

Max Act: 0.8423. Min Act: -0.0000

Data Index: 1740036 (The Pile)

Max Activating Token Index: 704

Text #18

Max Range: 1.4419. Min Range: -1.4419

Max Act: 0.8404. Min Act: -0.0000

Data Index: 1122680 (The Pile)

Max Activating Token Index: 103

Text #19

Max Range: 1.4419. Min Range: -1.4419

Max Act: 0.6981. Min Act: -0.0000

Data Index: 95120 (The Pile)

Max Activating Token Index: 1017