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

Dataset: The Pile

Neuron 2859 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: 0.4854. Min Range: -0.4854

Max Act: 0.4267. Min Act: -0.0000

Data Index: 1496926 (The Pile)

Max Activating Token Index: 756

Text #1

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.4854. Min Act: -0.0000

Data Index: 833046 (The Pile)

Max Activating Token Index: 597

Text #2

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.4068. Min Act: -0.0000

Data Index: 347870 (The Pile)

Max Activating Token Index: 825

Text #3

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3388. Min Act: -0.0000

Data Index: 1862468 (The Pile)

Max Activating Token Index: 931

Text #4

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3754. Min Act: -0.0000

Data Index: 1710334 (The Pile)

Max Activating Token Index: 763

Text #5

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3442. Min Act: -0.0000

Data Index: 410360 (The Pile)

Max Activating Token Index: 502

Text #6

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3336. Min Act: -0.0000

Data Index: 726612 (The Pile)

Max Activating Token Index: 483

Text #7

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.2804. Min Act: -0.0000

Data Index: 1589016 (The Pile)

Max Activating Token Index: 495

Text #8

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3332. Min Act: -0.0000

Data Index: 765857 (The Pile)

Max Activating Token Index: 418

Text #9

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3297. Min Act: -0.0000

Data Index: 1618657 (The Pile)

Max Activating Token Index: 714

Text #10

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.2903. Min Act: -0.0000

Data Index: 616634 (The Pile)

Max Activating Token Index: 698

Text #11

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.2887. Min Act: -0.0000

Data Index: 172637 (The Pile)

Max Activating Token Index: 354

Text #12

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.2880. Min Act: -0.0000

Data Index: 1128388 (The Pile)

Max Activating Token Index: 419

Text #13

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.2604. Min Act: -0.0000

Data Index: 1678864 (The Pile)

Max Activating Token Index: 987

Text #14

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.2682. Min Act: -0.0000

Data Index: 1439599 (The Pile)

Max Activating Token Index: 330

Text #15

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.2836. Min Act: -0.0000

Data Index: 1948438 (The Pile)

Max Activating Token Index: 277

Text #16

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.2709. Min Act: -0.0000

Data Index: 154780 (The Pile)

Max Activating Token Index: 216

Text #17

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.2660. Min Act: -0.0000

Data Index: 234492 (The Pile)

Max Activating Token Index: 341

Text #18

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.2573. Min Act: -0.0000

Data Index: 1697097 (The Pile)

Max Activating Token Index: 290

Text #19

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.2618. Min Act: -0.0000

Data Index: 1872370 (The Pile)

Max Activating Token Index: 528