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

Dataset: The Pile

Neuron 4099 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.7755. Min Act: -0.0000

Data Index: 581989 (The Pile)

Max Activating Token Index: 87

Text #1

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.7880. Min Act: -0.0000

Data Index: 1454491 (The Pile)

Max Activating Token Index: 25

Text #2

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.7647. Min Act: -0.0000

Data Index: 161763 (The Pile)

Max Activating Token Index: 144

Text #3

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.6622. Min Act: -0.0000

Data Index: 881760 (The Pile)

Max Activating Token Index: 71

Text #4

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.7181. Min Act: -0.0000

Data Index: 129536 (The Pile)

Max Activating Token Index: 53

Text #5

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.6432. Min Act: -0.0000

Data Index: 1664041 (The Pile)

Max Activating Token Index: 212

Text #6

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.6774. Min Act: -0.0000

Data Index: 1936306 (The Pile)

Max Activating Token Index: 24

Text #7

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.6496. Min Act: -0.0000

Data Index: 1204695 (The Pile)

Max Activating Token Index: 589

Text #8

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.6237. Min Act: -0.0000

Data Index: 1132089 (The Pile)

Max Activating Token Index: 939

Text #9

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.6393. Min Act: -0.0000

Data Index: 220636 (The Pile)

Max Activating Token Index: 422

Text #10

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.5984. Min Act: -0.0000

Data Index: 168979 (The Pile)

Max Activating Token Index: 92

Text #11

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.6011. Min Act: -0.0000

Data Index: 1080804 (The Pile)

Max Activating Token Index: 155

Text #12

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.6117. Min Act: -0.0000

Data Index: 1218445 (The Pile)

Max Activating Token Index: 78

Text #13

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.6025. Min Act: -0.0000

Data Index: 1855797 (The Pile)

Max Activating Token Index: 812

Text #14

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.6287. Min Act: -0.0000

Data Index: 1436945 (The Pile)

Max Activating Token Index: 118

Text #15

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.6122. Min Act: -0.0000

Data Index: 1658525 (The Pile)

Max Activating Token Index: 488

Text #16

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.5673. Min Act: -0.0000

Data Index: 556126 (The Pile)

Max Activating Token Index: 9

Text #17

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.6087. Min Act: -0.0000

Data Index: 1350467 (The Pile)

Max Activating Token Index: 875

Text #18

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.5409. Min Act: -0.0000

Data Index: 1623705 (The Pile)

Max Activating Token Index: 100

Text #19

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.5762. Min Act: -0.0000

Data Index: 1137067 (The Pile)

Max Activating Token Index: 721