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

Dataset: The Pile

Neuron 3404 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0678. Min Range: -1.0678

Max Act: 1.0425. Min Act: -0.0000

Data Index: 1901823 (The Pile)

Max Activating Token Index: 763

Text #1

Max Range: 1.0678. Min Range: -1.0678

Max Act: 1.0678. Min Act: -0.0000

Data Index: 434 (The Pile)

Max Activating Token Index: 877

Text #2

Max Range: 1.0678. Min Range: -1.0678

Max Act: 0.9411. Min Act: -0.0000

Data Index: 1648451 (The Pile)

Max Activating Token Index: 898

Text #3

Max Range: 1.0678. Min Range: -1.0678

Max Act: 0.8993. Min Act: -0.0000

Data Index: 723247 (The Pile)

Max Activating Token Index: 925

Text #4

Max Range: 1.0678. Min Range: -1.0678

Max Act: 0.8388. Min Act: -0.0000

Data Index: 1845541 (The Pile)

Max Activating Token Index: 680

Text #5

Max Range: 1.0678. Min Range: -1.0678

Max Act: 0.8632. Min Act: -0.0000

Data Index: 130744 (The Pile)

Max Activating Token Index: 958

Text #6

Max Range: 1.0678. Min Range: -1.0678

Max Act: 0.8610. Min Act: -0.0000

Data Index: 1723833 (The Pile)

Max Activating Token Index: 750

Text #7

Max Range: 1.0678. Min Range: -1.0678

Max Act: 0.7483. Min Act: -0.0000

Data Index: 1727034 (The Pile)

Max Activating Token Index: 699

Text #8

Max Range: 1.0678. Min Range: -1.0678

Max Act: 0.7087. Min Act: -0.0000

Data Index: 1463687 (The Pile)

Max Activating Token Index: 333

Text #9

Max Range: 1.0678. Min Range: -1.0678

Max Act: 0.8004. Min Act: -0.0000

Data Index: 876182 (The Pile)

Max Activating Token Index: 648

Text #10

Max Range: 1.0678. Min Range: -1.0678

Max Act: 0.7034. Min Act: -0.0000

Data Index: 1214825 (The Pile)

Max Activating Token Index: 922

Text #11

Max Range: 1.0678. Min Range: -1.0678

Max Act: 0.7341. Min Act: -0.0000

Data Index: 946262 (The Pile)

Max Activating Token Index: 971

Text #12

Max Range: 1.0678. Min Range: -1.0678

Max Act: 0.7070. Min Act: -0.0000

Data Index: 1709022 (The Pile)

Max Activating Token Index: 331

Text #13

Max Range: 1.0678. Min Range: -1.0678

Max Act: 0.7265. Min Act: -0.0000

Data Index: 1650770 (The Pile)

Max Activating Token Index: 416

Text #14

Max Range: 1.0678. Min Range: -1.0678

Max Act: 0.6797. Min Act: -0.0000

Data Index: 1857405 (The Pile)

Max Activating Token Index: 395

Text #15

Max Range: 1.0678. Min Range: -1.0678

Max Act: 0.7219. Min Act: -0.0000

Data Index: 938825 (The Pile)

Max Activating Token Index: 322

Text #16

Max Range: 1.0678. Min Range: -1.0678

Max Act: 0.6903. Min Act: -0.0000

Data Index: 688677 (The Pile)

Max Activating Token Index: 353

Text #17

Max Range: 1.0678. Min Range: -1.0678

Max Act: 0.7629. Min Act: -0.0000

Data Index: 476911 (The Pile)

Max Activating Token Index: 933

Text #18

Max Range: 1.0678. Min Range: -1.0678

Max Act: 0.6790. Min Act: -0.0000

Data Index: 1606381 (The Pile)

Max Activating Token Index: 26

Text #19

Max Range: 1.0678. Min Range: -1.0678

Max Act: 0.7055. Min Act: -0.0000

Data Index: 1185071 (The Pile)

Max Activating Token Index: 905