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

Dataset: The Pile

Neuron 250 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: 1.1653. Min Range: -1.1653

Max Act: 1.1653. Min Act: -0.0000

Data Index: 1284395 (The Pile)

Max Activating Token Index: 567

Text #1

Max Range: 1.1653. Min Range: -1.1653

Max Act: 0.9666. Min Act: -0.0000

Data Index: 1758851 (The Pile)

Max Activating Token Index: 1004

Text #2

Max Range: 1.1653. Min Range: -1.1653

Max Act: 0.8893. Min Act: -0.0000

Data Index: 85738 (The Pile)

Max Activating Token Index: 60

Text #3

Max Range: 1.1653. Min Range: -1.1653

Max Act: 0.8536. Min Act: -0.0000

Data Index: 746362 (The Pile)

Max Activating Token Index: 789

Text #4

Max Range: 1.1653. Min Range: -1.1653

Max Act: 0.8581. Min Act: -0.0000

Data Index: 1517611 (The Pile)

Max Activating Token Index: 169

Text #5

Max Range: 1.1653. Min Range: -1.1653

Max Act: 0.8547. Min Act: -0.0000

Data Index: 229481 (The Pile)

Max Activating Token Index: 107

Text #6

Max Range: 1.1653. Min Range: -1.1653

Max Act: 0.8749. Min Act: -0.0000

Data Index: 1817075 (The Pile)

Max Activating Token Index: 326

Text #7

Max Range: 1.1653. Min Range: -1.1653

Max Act: 0.8489. Min Act: -0.0000

Data Index: 1204009 (The Pile)

Max Activating Token Index: 782

Text #8

Max Range: 1.1653. Min Range: -1.1653

Max Act: 0.6166. Min Act: -0.0000

Data Index: 298621 (The Pile)

Max Activating Token Index: 830

Text #9

Max Range: 1.1653. Min Range: -1.1653

Max Act: 0.5775. Min Act: -0.0000

Data Index: 1758798 (The Pile)

Max Activating Token Index: 143

Text #10

Max Range: 1.1653. Min Range: -1.1653

Max Act: 0.5386. Min Act: -0.0000

Data Index: 1112916 (The Pile)

Max Activating Token Index: 838

Text #11

Max Range: 1.1653. Min Range: -1.1653

Max Act: 0.5018. Min Act: -0.0000

Data Index: 1382656 (The Pile)

Max Activating Token Index: 1018

Text #12

Max Range: 1.1653. Min Range: -1.1653

Max Act: 0.4845. Min Act: -0.0000

Data Index: 1701959 (The Pile)

Max Activating Token Index: 777

Text #13

Max Range: 1.1653. Min Range: -1.1653

Max Act: 0.4631. Min Act: -0.0000

Data Index: 1569387 (The Pile)

Max Activating Token Index: 429

Text #14

Max Range: 1.1653. Min Range: -1.1653

Max Act: 0.4916. Min Act: -0.0000

Data Index: 735566 (The Pile)

Max Activating Token Index: 55

Text #15

Max Range: 1.1653. Min Range: -1.1653

Max Act: 0.4657. Min Act: -0.0000

Data Index: 642435 (The Pile)

Max Activating Token Index: 585

Text #16

Max Range: 1.1653. Min Range: -1.1653

Max Act: 0.4628. Min Act: -0.0000

Data Index: 1539956 (The Pile)

Max Activating Token Index: 228

Text #17

Max Range: 1.1653. Min Range: -1.1653

Max Act: 0.4210. Min Act: -0.0000

Data Index: 216089 (The Pile)

Max Activating Token Index: 784

Text #18

Max Range: 1.1653. Min Range: -1.1653

Max Act: 0.4104. Min Act: -0.0000

Data Index: 1553544 (The Pile)

Max Activating Token Index: 97

Text #19

Max Range: 1.1653. Min Range: -1.1653

Max Act: 0.4671. Min Act: -0.0000

Data Index: 1177090 (The Pile)

Max Activating Token Index: 231