Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1497 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.7377. Min Act: -0.0000

Data Index: 1661149 (The Pile)

Max Activating Token Index: 56

Text #1

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.6621. Min Act: -0.0000

Data Index: 709134 (The Pile)

Max Activating Token Index: 114

Text #2

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.6520. Min Act: -0.0000

Data Index: 554447 (The Pile)

Max Activating Token Index: 131

Text #3

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5977. Min Act: -0.0000

Data Index: 253017 (The Pile)

Max Activating Token Index: 683

Text #4

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.6520. Min Act: -0.0000

Data Index: 644507 (The Pile)

Max Activating Token Index: 87

Text #5

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.6424. Min Act: -0.0000

Data Index: 1205756 (The Pile)

Max Activating Token Index: 188

Text #6

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.6053. Min Act: -0.0000

Data Index: 1167782 (The Pile)

Max Activating Token Index: 959

Text #7

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.6225. Min Act: -0.0000

Data Index: 1802305 (The Pile)

Max Activating Token Index: 1018

Text #8

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.6015. Min Act: -0.0000

Data Index: 1759478 (The Pile)

Max Activating Token Index: 987

Text #9

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5726. Min Act: -0.0000

Data Index: 1444653 (The Pile)

Max Activating Token Index: 672

Text #10

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5857. Min Act: -0.0000

Data Index: 1939615 (The Pile)

Max Activating Token Index: 106

Text #11

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5787. Min Act: -0.0000

Data Index: 495724 (The Pile)

Max Activating Token Index: 637

Text #12

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5433. Min Act: -0.0000

Data Index: 1346961 (The Pile)

Max Activating Token Index: 685

Text #13

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5804. Min Act: -0.0000

Data Index: 385088 (The Pile)

Max Activating Token Index: 454

Text #14

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5667. Min Act: -0.0000

Data Index: 511821 (The Pile)

Max Activating Token Index: 757

Text #15

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5479. Min Act: -0.0000

Data Index: 1852578 (The Pile)

Max Activating Token Index: 945

Text #16

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5774. Min Act: -0.0000

Data Index: 459586 (The Pile)

Max Activating Token Index: 206

Text #17

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5373. Min Act: -0.0000

Data Index: 1388595 (The Pile)

Max Activating Token Index: 569

Text #18

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5529. Min Act: -0.0000

Data Index: 1729776 (The Pile)

Max Activating Token Index: 1006

Text #19

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5268. Min Act: -0.0000

Data Index: 126326 (The Pile)

Max Activating Token Index: 426