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

Dataset: The Pile

Neuron 2644 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.9872. Min Act: -0.0000

Data Index: 1075651 (The Pile)

Max Activating Token Index: 1018

Text #1

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.9104. Min Act: -0.0000

Data Index: 1916603 (The Pile)

Max Activating Token Index: 748

Text #2

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.9462. Min Act: -0.0000

Data Index: 3334 (The Pile)

Max Activating Token Index: 794

Text #3

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.7451. Min Act: -0.0000

Data Index: 1302616 (The Pile)

Max Activating Token Index: 432

Text #4

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.7393. Min Act: -0.0000

Data Index: 1832509 (The Pile)

Max Activating Token Index: 224

Text #5

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.7368. Min Act: -0.0000

Data Index: 1581179 (The Pile)

Max Activating Token Index: 817

Text #6

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.7746. Min Act: -0.0000

Data Index: 1391873 (The Pile)

Max Activating Token Index: 8

Text #7

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.7125. Min Act: -0.0000

Data Index: 431211 (The Pile)

Max Activating Token Index: 471

Text #8

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.6962. Min Act: -0.0000

Data Index: 245325 (The Pile)

Max Activating Token Index: 301

Text #9

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.7095. Min Act: -0.0000

Data Index: 828428 (The Pile)

Max Activating Token Index: 588

Text #10

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.6347. Min Act: -0.0000

Data Index: 869160 (The Pile)

Max Activating Token Index: 164

Text #11

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.6338. Min Act: -0.0000

Data Index: 554546 (The Pile)

Max Activating Token Index: 436

Text #12

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.6077. Min Act: -0.0000

Data Index: 431425 (The Pile)

Max Activating Token Index: 1000

Text #13

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.6016. Min Act: -0.0000

Data Index: 698616 (The Pile)

Max Activating Token Index: 716

Text #14

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.6020. Min Act: -0.0000

Data Index: 1564928 (The Pile)

Max Activating Token Index: 408

Text #15

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.5860. Min Act: -0.0000

Data Index: 1816128 (The Pile)

Max Activating Token Index: 268

Text #16

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.5843. Min Act: -0.0000

Data Index: 1634707 (The Pile)

Max Activating Token Index: 530

Text #17

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.5819. Min Act: -0.0000

Data Index: 47076 (The Pile)

Max Activating Token Index: 626

Text #18

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.5538. Min Act: -0.0000

Data Index: 1841957 (The Pile)

Max Activating Token Index: 104

Text #19

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.5696. Min Act: -0.0000

Data Index: 1874078 (The Pile)

Max Activating Token Index: 33