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

Dataset: The Pile

Neuron 2752 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: 0.1380. Min Range: -0.1380

Max Act: 0.1380. Min Act: -0.0000

Data Index: 465482 (The Pile)

Max Activating Token Index: 289

Text #1

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1213. Min Act: -0.0000

Data Index: 191016 (The Pile)

Max Activating Token Index: 869

Text #2

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1118. Min Act: -0.0000

Data Index: 42590 (The Pile)

Max Activating Token Index: 507

Text #3

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1056. Min Act: -0.0000

Data Index: 1273320 (The Pile)

Max Activating Token Index: 826

Text #4

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1014. Min Act: -0.0000

Data Index: 1743780 (The Pile)

Max Activating Token Index: 220

Text #5

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0898. Min Act: -0.0000

Data Index: 984990 (The Pile)

Max Activating Token Index: 1020

Text #6

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1091. Min Act: -0.0000

Data Index: 409044 (The Pile)

Max Activating Token Index: 936

Text #7

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0966. Min Act: -0.0000

Data Index: 710767 (The Pile)

Max Activating Token Index: 1010

Text #8

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0989. Min Act: -0.0000

Data Index: 1082530 (The Pile)

Max Activating Token Index: 168

Text #9

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0948. Min Act: -0.0000

Data Index: 349499 (The Pile)

Max Activating Token Index: 389

Text #10

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0978. Min Act: -0.0000

Data Index: 1186985 (The Pile)

Max Activating Token Index: 472

Text #11

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0934. Min Act: -0.0000

Data Index: 1611447 (The Pile)

Max Activating Token Index: 741

Text #12

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0924. Min Act: -0.0000

Data Index: 1072437 (The Pile)

Max Activating Token Index: 175

Text #13

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0917. Min Act: -0.0000

Data Index: 324621 (The Pile)

Max Activating Token Index: 664

Text #14

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0933. Min Act: -0.0000

Data Index: 259569 (The Pile)

Max Activating Token Index: 826

Text #15

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0871. Min Act: -0.0000

Data Index: 1604970 (The Pile)

Max Activating Token Index: 503

Text #16

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0930. Min Act: -0.0000

Data Index: 847431 (The Pile)

Max Activating Token Index: 337

Text #17

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0985. Min Act: -0.0000

Data Index: 1019760 (The Pile)

Max Activating Token Index: 612

Text #18

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0886. Min Act: -0.0000

Data Index: 1012482 (The Pile)

Max Activating Token Index: 499

Text #19

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0987. Min Act: -0.0000

Data Index: 699192 (The Pile)

Max Activating Token Index: 675