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

Dataset: The Pile

Neuron 4916 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.8256. Min Act: -0.0000

Data Index: 1393703 (The Pile)

Max Activating Token Index: 434

Text #1

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.8341. Min Act: -0.0000

Data Index: 1078357 (The Pile)

Max Activating Token Index: 245

Text #2

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.7885. Min Act: -0.0000

Data Index: 1657622 (The Pile)

Max Activating Token Index: 637

Text #3

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.7317. Min Act: -0.0000

Data Index: 1867802 (The Pile)

Max Activating Token Index: 565

Text #4

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.6880. Min Act: -0.0000

Data Index: 1922142 (The Pile)

Max Activating Token Index: 980

Text #5

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.7356. Min Act: -0.0000

Data Index: 1653953 (The Pile)

Max Activating Token Index: 669

Text #6

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.6956. Min Act: -0.0000

Data Index: 641415 (The Pile)

Max Activating Token Index: 941

Text #7

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.6584. Min Act: -0.0000

Data Index: 1459850 (The Pile)

Max Activating Token Index: 517

Text #8

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.6356. Min Act: -0.0000

Data Index: 284686 (The Pile)

Max Activating Token Index: 99

Text #9

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.6330. Min Act: -0.0000

Data Index: 1636887 (The Pile)

Max Activating Token Index: 60

Text #10

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.6476. Min Act: -0.0000

Data Index: 721532 (The Pile)

Max Activating Token Index: 912

Text #11

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.5958. Min Act: -0.0000

Data Index: 1517328 (The Pile)

Max Activating Token Index: 810

Text #12

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.6284. Min Act: -0.0000

Data Index: 748719 (The Pile)

Max Activating Token Index: 1008

Text #13

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.6046. Min Act: -0.0000

Data Index: 990247 (The Pile)

Max Activating Token Index: 600

Text #14

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.5646. Min Act: -0.0000

Data Index: 734333 (The Pile)

Max Activating Token Index: 818

Text #15

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.6347. Min Act: -0.0000

Data Index: 371496 (The Pile)

Max Activating Token Index: 103

Text #16

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.5872. Min Act: -0.0000

Data Index: 165011 (The Pile)

Max Activating Token Index: 183

Text #17

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.5975. Min Act: -0.0000

Data Index: 1013918 (The Pile)

Max Activating Token Index: 140

Text #18

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.5842. Min Act: -0.0000

Data Index: 1364139 (The Pile)

Max Activating Token Index: 554

Text #19

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.5767. Min Act: -0.0000

Data Index: 816933 (The Pile)

Max Activating Token Index: 338