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

Dataset: The Pile

Neuron 389 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.8298. Min Act: -0.0000

Data Index: 979216 (The Pile)

Max Activating Token Index: 132

Text #1

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.7631. Min Act: -0.0000

Data Index: 694844 (The Pile)

Max Activating Token Index: 517

Text #2

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.6583. Min Act: -0.0000

Data Index: 726956 (The Pile)

Max Activating Token Index: 382

Text #3

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.6652. Min Act: -0.0000

Data Index: 1222660 (The Pile)

Max Activating Token Index: 485

Text #4

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.6414. Min Act: -0.0000

Data Index: 1124410 (The Pile)

Max Activating Token Index: 628

Text #5

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.6785. Min Act: -0.0000

Data Index: 354025 (The Pile)

Max Activating Token Index: 644

Text #6

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.6832. Min Act: -0.0000

Data Index: 1351458 (The Pile)

Max Activating Token Index: 36

Text #7

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.6554. Min Act: -0.0000

Data Index: 523797 (The Pile)

Max Activating Token Index: 435

Text #8

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.6576. Min Act: -0.0000

Data Index: 169558 (The Pile)

Max Activating Token Index: 228

Text #9

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.6695. Min Act: -0.0000

Data Index: 1896415 (The Pile)

Max Activating Token Index: 337

Text #10

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.6015. Min Act: -0.0000

Data Index: 932703 (The Pile)

Max Activating Token Index: 705

Text #11

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.5357. Min Act: -0.0000

Data Index: 1371923 (The Pile)

Max Activating Token Index: 399

Text #12

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.6187. Min Act: -0.0000

Data Index: 774956 (The Pile)

Max Activating Token Index: 85

Text #13

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.6847. Min Act: -0.0000

Data Index: 71450 (The Pile)

Max Activating Token Index: 628

Text #14

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.5827. Min Act: -0.0000

Data Index: 349763 (The Pile)

Max Activating Token Index: 699

Text #15

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.6068. Min Act: -0.0000

Data Index: 586300 (The Pile)

Max Activating Token Index: 747

Text #16

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.5380. Min Act: -0.0000

Data Index: 1359343 (The Pile)

Max Activating Token Index: 184

Text #17

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.5800. Min Act: -0.0000

Data Index: 1710006 (The Pile)

Max Activating Token Index: 846

Text #18

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.5987. Min Act: -0.0000

Data Index: 792983 (The Pile)

Max Activating Token Index: 140

Text #19

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.5857. Min Act: -0.0000

Data Index: 573533 (The Pile)

Max Activating Token Index: 118