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

Dataset: The Pile

Neuron 172 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.9557. Min Act: -0.0000

Data Index: 1280102 (The Pile)

Max Activating Token Index: 903

Text #1

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.6342. Min Act: -0.0000

Data Index: 708094 (The Pile)

Max Activating Token Index: 975

Text #2

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.6400. Min Act: -0.0000

Data Index: 1078164 (The Pile)

Max Activating Token Index: 343

Text #3

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.5821. Min Act: -0.0000

Data Index: 1193945 (The Pile)

Max Activating Token Index: 815

Text #4

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.4422. Min Act: -0.0000

Data Index: 1415605 (The Pile)

Max Activating Token Index: 645

Text #5

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.5199. Min Act: -0.0000

Data Index: 491992 (The Pile)

Max Activating Token Index: 850

Text #6

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.4669. Min Act: -0.0000

Data Index: 1249070 (The Pile)

Max Activating Token Index: 756

Text #7

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.3463. Min Act: -0.0000

Data Index: 1687629 (The Pile)

Max Activating Token Index: 726

Text #8

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.5671. Min Act: -0.0000

Data Index: 1785459 (The Pile)

Max Activating Token Index: 808

Text #9

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.5203. Min Act: -0.0000

Data Index: 1866676 (The Pile)

Max Activating Token Index: 975

Text #10

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.5146. Min Act: -0.0000

Data Index: 1850131 (The Pile)

Max Activating Token Index: 629

Text #11

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.4836. Min Act: -0.0000

Data Index: 260983 (The Pile)

Max Activating Token Index: 1011

Text #12

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.4623. Min Act: -0.0000

Data Index: 19257 (The Pile)

Max Activating Token Index: 542

Text #13

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.4904. Min Act: -0.0000

Data Index: 1025515 (The Pile)

Max Activating Token Index: 332

Text #14

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.4434. Min Act: -0.0000

Data Index: 1009548 (The Pile)

Max Activating Token Index: 351

Text #15

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.4833. Min Act: -0.0000

Data Index: 919035 (The Pile)

Max Activating Token Index: 275

Text #16

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.4909. Min Act: -0.0000

Data Index: 328140 (The Pile)

Max Activating Token Index: 364

Text #17

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.4057. Min Act: -0.0000

Data Index: 1634908 (The Pile)

Max Activating Token Index: 835

Text #18

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.4177. Min Act: -0.0000

Data Index: 1357426 (The Pile)

Max Activating Token Index: 122

Text #19

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.4112. Min Act: -0.0000

Data Index: 1013135 (The Pile)

Max Activating Token Index: 239