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

Dataset: The Pile

Neuron 2228 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3442. Min Range: -1.3442

Max Act: 1.3442. Min Act: -0.0000

Data Index: 1476872 (The Pile)

Max Activating Token Index: 34

Text #1

Max Range: 1.3442. Min Range: -1.3442

Max Act: 1.3294. Min Act: -0.0000

Data Index: 1180761 (The Pile)

Max Activating Token Index: 95

Text #2

Max Range: 1.3442. Min Range: -1.3442

Max Act: 1.2541. Min Act: 0.0000

Data Index: 1469974 (The Pile)

Max Activating Token Index: 136

Text #3

Max Range: 1.3442. Min Range: -1.3442

Max Act: 1.2394. Min Act: -0.0000

Data Index: 1603447 (The Pile)

Max Activating Token Index: 739

Text #4

Max Range: 1.3442. Min Range: -1.3442

Max Act: 1.3080. Min Act: -0.0000

Data Index: 985423 (The Pile)

Max Activating Token Index: 22

Text #5

Max Range: 1.3442. Min Range: -1.3442

Max Act: 1.1565. Min Act: 0.0000

Data Index: 899316 (The Pile)

Max Activating Token Index: 580

Text #6

Max Range: 1.3442. Min Range: -1.3442

Max Act: 1.1866. Min Act: -0.0000

Data Index: 1006552 (The Pile)

Max Activating Token Index: 867

Text #7

Max Range: 1.3442. Min Range: -1.3442

Max Act: 1.1746. Min Act: -0.0000

Data Index: 707367 (The Pile)

Max Activating Token Index: 97

Text #8

Max Range: 1.3442. Min Range: -1.3442

Max Act: 1.2412. Min Act: 0.0000

Data Index: 1212368 (The Pile)

Max Activating Token Index: 788

Text #9

Max Range: 1.3442. Min Range: -1.3442

Max Act: 1.1725. Min Act: -0.0000

Data Index: 1061742 (The Pile)

Max Activating Token Index: 469

Text #10

Max Range: 1.3442. Min Range: -1.3442

Max Act: 1.1554. Min Act: 0.0000

Data Index: 1786886 (The Pile)

Max Activating Token Index: 57

Text #11

Max Range: 1.3442. Min Range: -1.3442

Max Act: 1.1471. Min Act: -0.0000

Data Index: 1059090 (The Pile)

Max Activating Token Index: 930

Text #12

Max Range: 1.3442. Min Range: -1.3442

Max Act: 1.0903. Min Act: -0.0000

Data Index: 1603843 (The Pile)

Max Activating Token Index: 208

Text #13

Max Range: 1.3442. Min Range: -1.3442

Max Act: 1.0720. Min Act: -0.0000

Data Index: 1442095 (The Pile)

Max Activating Token Index: 745

Text #14

Max Range: 1.3442. Min Range: -1.3442

Max Act: 0.9911. Min Act: -0.0000

Data Index: 1429072 (The Pile)

Max Activating Token Index: 745

Text #15

Max Range: 1.3442. Min Range: -1.3442

Max Act: 0.9976. Min Act: -0.0000

Data Index: 1776307 (The Pile)

Max Activating Token Index: 239

Text #16

Max Range: 1.3442. Min Range: -1.3442

Max Act: 1.0600. Min Act: 0.0001

Data Index: 1601073 (The Pile)

Max Activating Token Index: 19

Text #17

Max Range: 1.3442. Min Range: -1.3442

Max Act: 1.0516. Min Act: -0.0000

Data Index: 408856 (The Pile)

Max Activating Token Index: 196

Text #18

Max Range: 1.3442. Min Range: -1.3442

Max Act: 0.9600. Min Act: -0.0000

Data Index: 957237 (The Pile)

Max Activating Token Index: 977

Text #19

Max Range: 1.3442. Min Range: -1.3442

Max Act: 1.0325. Min Act: -0.0000

Data Index: 1788421 (The Pile)

Max Activating Token Index: 323