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

Dataset: The Pile

Neuron 475 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: 0.9434. Min Range: -0.9434

Max Act: 0.9434. Min Act: -0.0000

Data Index: 1336617 (The Pile)

Max Activating Token Index: 39

Text #1

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.8843. Min Act: -0.0000

Data Index: 1119393 (The Pile)

Max Activating Token Index: 297

Text #2

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.8903. Min Act: -0.0000

Data Index: 1978570 (The Pile)

Max Activating Token Index: 297

Text #3

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.8254. Min Act: -0.0000

Data Index: 806933 (The Pile)

Max Activating Token Index: 139

Text #4

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.8030. Min Act: -0.0000

Data Index: 727960 (The Pile)

Max Activating Token Index: 766

Text #5

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.8096. Min Act: -0.0000

Data Index: 1757026 (The Pile)

Max Activating Token Index: 874

Text #6

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.7723. Min Act: -0.0000

Data Index: 27647 (The Pile)

Max Activating Token Index: 970

Text #7

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.7950. Min Act: -0.0000

Data Index: 681055 (The Pile)

Max Activating Token Index: 366

Text #8

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.7868. Min Act: -0.0000

Data Index: 658954 (The Pile)

Max Activating Token Index: 465

Text #9

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.7481. Min Act: -0.0000

Data Index: 1948942 (The Pile)

Max Activating Token Index: 351

Text #10

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.7470. Min Act: -0.0000

Data Index: 297771 (The Pile)

Max Activating Token Index: 617

Text #11

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.7672. Min Act: -0.0000

Data Index: 138194 (The Pile)

Max Activating Token Index: 1003

Text #12

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.7923. Min Act: -0.0000

Data Index: 1193907 (The Pile)

Max Activating Token Index: 327

Text #13

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.8187. Min Act: -0.0000

Data Index: 927218 (The Pile)

Max Activating Token Index: 195

Text #14

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.7855. Min Act: -0.0000

Data Index: 1433964 (The Pile)

Max Activating Token Index: 435

Text #15

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.7673. Min Act: -0.0000

Data Index: 1091931 (The Pile)

Max Activating Token Index: 695

Text #16

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.7836. Min Act: -0.0000

Data Index: 580632 (The Pile)

Max Activating Token Index: 962

Text #17

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.7820. Min Act: -0.0000

Data Index: 835014 (The Pile)

Max Activating Token Index: 659

Text #18

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.7578. Min Act: -0.0000

Data Index: 9148 (The Pile)

Max Activating Token Index: 533

Text #19

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.7284. Min Act: -0.0000

Data Index: 979536 (The Pile)

Max Activating Token Index: 356