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

Dataset: The Pile

Neuron 1394 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4806. Min Range: -3.4806

Max Act: 3.3340. Min Act: -0.0000

Data Index: 795942 (The Pile)

Max Activating Token Index: 577

Text #1

Max Range: 3.4806. Min Range: -3.4806

Max Act: 3.4806. Min Act: -0.0000

Data Index: 1511367 (The Pile)

Max Activating Token Index: 958

Text #2

Max Range: 3.4806. Min Range: -3.4806

Max Act: 2.4933. Min Act: -0.0000

Data Index: 419223 (The Pile)

Max Activating Token Index: 696

Text #3

Max Range: 3.4806. Min Range: -3.4806

Max Act: 3.0187. Min Act: -0.0000

Data Index: 938283 (The Pile)

Max Activating Token Index: 923

Text #4

Max Range: 3.4806. Min Range: -3.4806

Max Act: 2.6844. Min Act: -0.0000

Data Index: 1597857 (The Pile)

Max Activating Token Index: 612

Text #5

Max Range: 3.4806. Min Range: -3.4806

Max Act: 2.3422. Min Act: -0.0000

Data Index: 788337 (The Pile)

Max Activating Token Index: 837

Text #6

Max Range: 3.4806. Min Range: -3.4806

Max Act: 2.4071. Min Act: -0.0000

Data Index: 1531787 (The Pile)

Max Activating Token Index: 418

Text #7

Max Range: 3.4806. Min Range: -3.4806

Max Act: 2.2577. Min Act: -0.0000

Data Index: 1401681 (The Pile)

Max Activating Token Index: 468

Text #8

Max Range: 3.4806. Min Range: -3.4806

Max Act: 2.5842. Min Act: -0.0000

Data Index: 1319971 (The Pile)

Max Activating Token Index: 760

Text #9

Max Range: 3.4806. Min Range: -3.4806

Max Act: 2.1894. Min Act: -0.0000

Data Index: 53324 (The Pile)

Max Activating Token Index: 148

Text #10

Max Range: 3.4806. Min Range: -3.4806

Max Act: 2.2871. Min Act: -0.0000

Data Index: 87275 (The Pile)

Max Activating Token Index: 560

Text #11

Max Range: 3.4806. Min Range: -3.4806

Max Act: 2.2863. Min Act: -0.0000

Data Index: 1753871 (The Pile)

Max Activating Token Index: 661

Text #12

Max Range: 3.4806. Min Range: -3.4806

Max Act: 2.2590. Min Act: -0.0000

Data Index: 928161 (The Pile)

Max Activating Token Index: 310

Text #13

Max Range: 3.4806. Min Range: -3.4806

Max Act: 2.3705. Min Act: -0.0000

Data Index: 1643017 (The Pile)

Max Activating Token Index: 748

Text #14

Max Range: 3.4806. Min Range: -3.4806

Max Act: 2.0881. Min Act: -0.0000

Data Index: 274593 (The Pile)

Max Activating Token Index: 434

Text #15

Max Range: 3.4806. Min Range: -3.4806

Max Act: 2.1610. Min Act: -0.0000

Data Index: 117292 (The Pile)

Max Activating Token Index: 194

Text #16

Max Range: 3.4806. Min Range: -3.4806

Max Act: 2.1601. Min Act: -0.0000

Data Index: 1003618 (The Pile)

Max Activating Token Index: 811

Text #17

Max Range: 3.4806. Min Range: -3.4806

Max Act: 1.8926. Min Act: -0.0000

Data Index: 538932 (The Pile)

Max Activating Token Index: 964

Text #18

Max Range: 3.4806. Min Range: -3.4806

Max Act: 2.1049. Min Act: -0.0000

Data Index: 181549 (The Pile)

Max Activating Token Index: 577

Text #19

Max Range: 3.4806. Min Range: -3.4806

Max Act: 2.0764. Min Act: -0.0000

Data Index: 200568 (The Pile)

Max Activating Token Index: 109