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

Dataset: The Pile

Neuron 64 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.8786. Min Range: -1.8786

Max Act: 1.8786. Min Act: 0.0000

Data Index: 704106 (The Pile)

Max Activating Token Index: 415

Text #1

Max Range: 1.8786. Min Range: -1.8786

Max Act: 1.8570. Min Act: -0.0000

Data Index: 215500 (The Pile)

Max Activating Token Index: 611

Text #2

Max Range: 1.8786. Min Range: -1.8786

Max Act: 1.6609. Min Act: -0.0000

Data Index: 1913540 (The Pile)

Max Activating Token Index: 431

Text #3

Max Range: 1.8786. Min Range: -1.8786

Max Act: 1.6461. Min Act: -0.0000

Data Index: 1472246 (The Pile)

Max Activating Token Index: 413

Text #4

Max Range: 1.8786. Min Range: -1.8786

Max Act: 1.7340. Min Act: -0.0000

Data Index: 1235533 (The Pile)

Max Activating Token Index: 561

Text #5

Max Range: 1.8786. Min Range: -1.8786

Max Act: 1.6301. Min Act: -0.0000

Data Index: 1477839 (The Pile)

Max Activating Token Index: 483

Text #6

Max Range: 1.8786. Min Range: -1.8786

Max Act: 1.6854. Min Act: -0.0000

Data Index: 934637 (The Pile)

Max Activating Token Index: 471

Text #7

Max Range: 1.8786. Min Range: -1.8786

Max Act: 1.7026. Min Act: -0.0000

Data Index: 730611 (The Pile)

Max Activating Token Index: 666

Text #8

Max Range: 1.8786. Min Range: -1.8786

Max Act: 1.6961. Min Act: -0.0000

Data Index: 701281 (The Pile)

Max Activating Token Index: 643

Text #9

Max Range: 1.8786. Min Range: -1.8786

Max Act: 1.6797. Min Act: -0.0000

Data Index: 639460 (The Pile)

Max Activating Token Index: 261

Text #10

Max Range: 1.8786. Min Range: -1.8786

Max Act: 1.6757. Min Act: -0.0000

Data Index: 935077 (The Pile)

Max Activating Token Index: 756

Text #11

Max Range: 1.8786. Min Range: -1.8786

Max Act: 1.7709. Min Act: -0.0000

Data Index: 385771 (The Pile)

Max Activating Token Index: 350

Text #12

Max Range: 1.8786. Min Range: -1.8786

Max Act: 1.6365. Min Act: -0.0000

Data Index: 1002242 (The Pile)

Max Activating Token Index: 607

Text #13

Max Range: 1.8786. Min Range: -1.8786

Max Act: 1.5966. Min Act: -0.0000

Data Index: 1493564 (The Pile)

Max Activating Token Index: 290

Text #14

Max Range: 1.8786. Min Range: -1.8786

Max Act: 1.4805. Min Act: -0.0000

Data Index: 192176 (The Pile)

Max Activating Token Index: 567

Text #15

Max Range: 1.8786. Min Range: -1.8786

Max Act: 1.5807. Min Act: -0.0000

Data Index: 1432941 (The Pile)

Max Activating Token Index: 621

Text #16

Max Range: 1.8786. Min Range: -1.8786

Max Act: 1.5636. Min Act: -0.0000

Data Index: 1944462 (The Pile)

Max Activating Token Index: 603

Text #17

Max Range: 1.8786. Min Range: -1.8786

Max Act: 1.5741. Min Act: -0.0000

Data Index: 1713796 (The Pile)

Max Activating Token Index: 651

Text #18

Max Range: 1.8786. Min Range: -1.8786

Max Act: 1.6528. Min Act: -0.0000

Data Index: 681299 (The Pile)

Max Activating Token Index: 411

Text #19

Max Range: 1.8786. Min Range: -1.8786

Max Act: 1.5653. Min Act: -0.0000

Data Index: 73624 (The Pile)

Max Activating Token Index: 346