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

Dataset: The Pile

Neuron 465 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1253. Min Act: -0.0000

Data Index: 1049383 (The Pile)

Max Activating Token Index: 1019

Text #1

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1281. Min Act: -0.0000

Data Index: 1670295 (The Pile)

Max Activating Token Index: 272

Text #2

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1138. Min Act: -0.0000

Data Index: 1765243 (The Pile)

Max Activating Token Index: 513

Text #3

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1092. Min Act: -0.0000

Data Index: 575644 (The Pile)

Max Activating Token Index: 327

Text #4

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1026. Min Act: -0.0000

Data Index: 1384686 (The Pile)

Max Activating Token Index: 340

Text #5

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0916. Min Act: -0.0000

Data Index: 95085 (The Pile)

Max Activating Token Index: 733

Text #6

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1031. Min Act: -0.0000

Data Index: 606800 (The Pile)

Max Activating Token Index: 928

Text #7

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1025. Min Act: -0.0000

Data Index: 282413 (The Pile)

Max Activating Token Index: 304

Text #8

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0946. Min Act: -0.0000

Data Index: 410234 (The Pile)

Max Activating Token Index: 683

Text #9

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0873. Min Act: -0.0000

Data Index: 773368 (The Pile)

Max Activating Token Index: 721

Text #10

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0773. Min Act: -0.0000

Data Index: 531827 (The Pile)

Max Activating Token Index: 823

Text #11

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0817. Min Act: -0.0000

Data Index: 520015 (The Pile)

Max Activating Token Index: 932

Text #12

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0884. Min Act: -0.0000

Data Index: 610453 (The Pile)

Max Activating Token Index: 640

Text #13

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0819. Min Act: -0.0000

Data Index: 1239396 (The Pile)

Max Activating Token Index: 768

Text #14

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0898. Min Act: -0.0000

Data Index: 627460 (The Pile)

Max Activating Token Index: 270

Text #15

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0883. Min Act: -0.0001

Data Index: 1757204 (The Pile)

Max Activating Token Index: 399

Text #16

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0856. Min Act: -0.0000

Data Index: 866320 (The Pile)

Max Activating Token Index: 374

Text #17

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0881. Min Act: -0.0000

Data Index: 629600 (The Pile)

Max Activating Token Index: 744

Text #18

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0721. Min Act: -0.0000

Data Index: 931506 (The Pile)

Max Activating Token Index: 893

Text #19

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0846. Min Act: -0.0000

Data Index: 1282319 (The Pile)

Max Activating Token Index: 339