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

Dataset: The Pile

Neuron 2559 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: 0.7260. Min Range: -0.7260

Max Act: 0.6813. Min Act: 0.0000

Data Index: 1282846 (The Pile)

Max Activating Token Index: 763

Text #1

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.7260. Min Act: -0.0000

Data Index: 1633386 (The Pile)

Max Activating Token Index: 817

Text #2

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.5584. Min Act: 0.0000

Data Index: 1843722 (The Pile)

Max Activating Token Index: 965

Text #3

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.5905. Min Act: -0.0000

Data Index: 252139 (The Pile)

Max Activating Token Index: 685

Text #4

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.5790. Min Act: -0.0000

Data Index: 931082 (The Pile)

Max Activating Token Index: 846

Text #5

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.5509. Min Act: -0.0000

Data Index: 695150 (The Pile)

Max Activating Token Index: 973

Text #6

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.4874. Min Act: -0.0000

Data Index: 1160902 (The Pile)

Max Activating Token Index: 975

Text #7

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.5230. Min Act: -0.0000

Data Index: 459181 (The Pile)

Max Activating Token Index: 691

Text #8

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.5146. Min Act: -0.0000

Data Index: 585140 (The Pile)

Max Activating Token Index: 317

Text #9

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.4788. Min Act: -0.0000

Data Index: 521768 (The Pile)

Max Activating Token Index: 831

Text #10

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.4630. Min Act: -0.0000

Data Index: 760448 (The Pile)

Max Activating Token Index: 628

Text #11

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.4480. Min Act: -0.0000

Data Index: 1590820 (The Pile)

Max Activating Token Index: 829

Text #12

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.4974. Min Act: -0.0000

Data Index: 721411 (The Pile)

Max Activating Token Index: 413

Text #13

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.4901. Min Act: -0.0000

Data Index: 1437489 (The Pile)

Max Activating Token Index: 96

Text #14

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.5152. Min Act: -0.0000

Data Index: 879057 (The Pile)

Max Activating Token Index: 979

Text #15

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.4758. Min Act: 0.0000

Data Index: 231164 (The Pile)

Max Activating Token Index: 813

Text #16

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.4370. Min Act: -0.0000

Data Index: 851683 (The Pile)

Max Activating Token Index: 754

Text #17

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.4806. Min Act: -0.0000

Data Index: 1137851 (The Pile)

Max Activating Token Index: 695

Text #18

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.4706. Min Act: -0.0000

Data Index: 1466317 (The Pile)

Max Activating Token Index: 565

Text #19

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.4915. Min Act: -0.0000

Data Index: 513947 (The Pile)

Max Activating Token Index: 529