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

Dataset: The Pile

Neuron 3297 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: 3.6666. Min Range: -3.6666

Max Act: 3.6666. Min Act: -0.0000

Data Index: 1649297 (The Pile)

Max Activating Token Index: 3

Text #1

Max Range: 3.6666. Min Range: -3.6666

Max Act: 3.5023. Min Act: -0.0000

Data Index: 854638 (The Pile)

Max Activating Token Index: 56

Text #2

Max Range: 3.6666. Min Range: -3.6666

Max Act: 3.4241. Min Act: -0.0000

Data Index: 1924702 (The Pile)

Max Activating Token Index: 459

Text #3

Max Range: 3.6666. Min Range: -3.6666

Max Act: 3.1975. Min Act: -0.0000

Data Index: 1948008 (The Pile)

Max Activating Token Index: 842

Text #4

Max Range: 3.6666. Min Range: -3.6666

Max Act: 3.3509. Min Act: -0.0000

Data Index: 1463766 (The Pile)

Max Activating Token Index: 563

Text #5

Max Range: 3.6666. Min Range: -3.6666

Max Act: 3.3393. Min Act: -0.0000

Data Index: 713919 (The Pile)

Max Activating Token Index: 43

Text #6

Max Range: 3.6666. Min Range: -3.6666

Max Act: 3.1414. Min Act: -0.0000

Data Index: 218489 (The Pile)

Max Activating Token Index: 753

Text #7

Max Range: 3.6666. Min Range: -3.6666

Max Act: 3.3681. Min Act: -0.0000

Data Index: 1626423 (The Pile)

Max Activating Token Index: 181

Text #8

Max Range: 3.6666. Min Range: -3.6666

Max Act: 3.1833. Min Act: -0.0000

Data Index: 1995330 (The Pile)

Max Activating Token Index: 160

Text #9

Max Range: 3.6666. Min Range: -3.6666

Max Act: 3.0423. Min Act: -0.0000

Data Index: 555219 (The Pile)

Max Activating Token Index: 686

Text #10

Max Range: 3.6666. Min Range: -3.6666

Max Act: 3.1674. Min Act: -0.0000

Data Index: 92135 (The Pile)

Max Activating Token Index: 413

Text #11

Max Range: 3.6666. Min Range: -3.6666

Max Act: 3.0395. Min Act: -0.0000

Data Index: 1336101 (The Pile)

Max Activating Token Index: 931

Text #12

Max Range: 3.6666. Min Range: -3.6666

Max Act: 2.9734. Min Act: -0.0000

Data Index: 110801 (The Pile)

Max Activating Token Index: 461

Text #13

Max Range: 3.6666. Min Range: -3.6666

Max Act: 3.0866. Min Act: -0.0000

Data Index: 1646957 (The Pile)

Max Activating Token Index: 573

Text #14

Max Range: 3.6666. Min Range: -3.6666

Max Act: 3.2479. Min Act: -0.0000

Data Index: 1023541 (The Pile)

Max Activating Token Index: 342

Text #15

Max Range: 3.6666. Min Range: -3.6666

Max Act: 3.0893. Min Act: -0.0000

Data Index: 1843487 (The Pile)

Max Activating Token Index: 6

Text #16

Max Range: 3.6666. Min Range: -3.6666

Max Act: 3.0423. Min Act: -0.0000

Data Index: 1733528 (The Pile)

Max Activating Token Index: 211

Text #17

Max Range: 3.6666. Min Range: -3.6666

Max Act: 3.0051. Min Act: -0.0000

Data Index: 1934242 (The Pile)

Max Activating Token Index: 483

Text #18

Max Range: 3.6666. Min Range: -3.6666

Max Act: 2.9898. Min Act: -0.0000

Data Index: 931942 (The Pile)

Max Activating Token Index: 24

Text #19

Max Range: 3.6666. Min Range: -3.6666

Max Act: 2.8315. Min Act: -0.0000

Data Index: 914504 (The Pile)

Max Activating Token Index: 946