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

Dataset: The Pile

Neuron 3849 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: 1.2704. Min Range: -1.2704

Max Act: 1.1640. Min Act: -0.0000

Data Index: 284350 (The Pile)

Max Activating Token Index: 997

Text #1

Max Range: 1.2704. Min Range: -1.2704

Max Act: 1.2704. Min Act: -0.0000

Data Index: 1692799 (The Pile)

Max Activating Token Index: 204

Text #2

Max Range: 1.2704. Min Range: -1.2704

Max Act: 1.0410. Min Act: -0.0000

Data Index: 278639 (The Pile)

Max Activating Token Index: 702

Text #3

Max Range: 1.2704. Min Range: -1.2704

Max Act: 0.9103. Min Act: -0.0000

Data Index: 1031399 (The Pile)

Max Activating Token Index: 413

Text #4

Max Range: 1.2704. Min Range: -1.2704

Max Act: 0.9309. Min Act: -0.0000

Data Index: 1299952 (The Pile)

Max Activating Token Index: 742

Text #5

Max Range: 1.2704. Min Range: -1.2704

Max Act: 0.9738. Min Act: -0.0000

Data Index: 1516963 (The Pile)

Max Activating Token Index: 252

Text #6

Max Range: 1.2704. Min Range: -1.2704

Max Act: 0.9062. Min Act: -0.0000

Data Index: 755883 (The Pile)

Max Activating Token Index: 949

Text #7

Max Range: 1.2704. Min Range: -1.2704

Max Act: 0.8812. Min Act: -0.0000

Data Index: 1702 (The Pile)

Max Activating Token Index: 466

Text #8

Max Range: 1.2704. Min Range: -1.2704

Max Act: 0.9073. Min Act: -0.0000

Data Index: 152461 (The Pile)

Max Activating Token Index: 307

Text #9

Max Range: 1.2704. Min Range: -1.2704

Max Act: 0.9270. Min Act: -0.0000

Data Index: 768518 (The Pile)

Max Activating Token Index: 396

Text #10

Max Range: 1.2704. Min Range: -1.2704

Max Act: 0.9111. Min Act: -0.0000

Data Index: 785680 (The Pile)

Max Activating Token Index: 513

Text #11

Max Range: 1.2704. Min Range: -1.2704

Max Act: 0.9329. Min Act: -0.0000

Data Index: 303132 (The Pile)

Max Activating Token Index: 653

Text #12

Max Range: 1.2704. Min Range: -1.2704

Max Act: 0.8777. Min Act: -0.0000

Data Index: 1390080 (The Pile)

Max Activating Token Index: 998

Text #13

Max Range: 1.2704. Min Range: -1.2704

Max Act: 0.9515. Min Act: -0.0000

Data Index: 826558 (The Pile)

Max Activating Token Index: 524

Text #14

Max Range: 1.2704. Min Range: -1.2704

Max Act: 0.8829. Min Act: -0.0000

Data Index: 1154609 (The Pile)

Max Activating Token Index: 918

Text #15

Max Range: 1.2704. Min Range: -1.2704

Max Act: 0.8237. Min Act: -0.0000

Data Index: 288730 (The Pile)

Max Activating Token Index: 803

Text #16

Max Range: 1.2704. Min Range: -1.2704

Max Act: 0.9593. Min Act: -0.0000

Data Index: 312006 (The Pile)

Max Activating Token Index: 947

Text #17

Max Range: 1.2704. Min Range: -1.2704

Max Act: 0.8523. Min Act: -0.0000

Data Index: 1031725 (The Pile)

Max Activating Token Index: 493

Text #18

Max Range: 1.2704. Min Range: -1.2704

Max Act: 0.9334. Min Act: -0.0000

Data Index: 1981303 (The Pile)

Max Activating Token Index: 672

Text #19

Max Range: 1.2704. Min Range: -1.2704

Max Act: 0.8135. Min Act: -0.0000

Data Index: 1963902 (The Pile)

Max Activating Token Index: 704