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

Dataset: The Pile

Neuron 1673 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: 1.9123. Min Range: -1.9123

Max Act: 1.8279. Min Act: -0.0000

Data Index: 1180579 (The Pile)

Max Activating Token Index: 165

Text #1

Max Range: 1.9123. Min Range: -1.9123

Max Act: 1.9123. Min Act: -0.0000

Data Index: 1298616 (The Pile)

Max Activating Token Index: 994

Text #2

Max Range: 1.9123. Min Range: -1.9123

Max Act: 1.8023. Min Act: -0.0000

Data Index: 1524125 (The Pile)

Max Activating Token Index: 37

Text #3

Max Range: 1.9123. Min Range: -1.9123

Max Act: 1.6807. Min Act: -0.0000

Data Index: 1055144 (The Pile)

Max Activating Token Index: 363

Text #4

Max Range: 1.9123. Min Range: -1.9123

Max Act: 1.6443. Min Act: -0.0000

Data Index: 4855 (The Pile)

Max Activating Token Index: 865

Text #5

Max Range: 1.9123. Min Range: -1.9123

Max Act: 1.5719. Min Act: -0.0000

Data Index: 314705 (The Pile)

Max Activating Token Index: 1001

Text #6

Max Range: 1.9123. Min Range: -1.9123

Max Act: 1.5078. Min Act: -0.0000

Data Index: 234837 (The Pile)

Max Activating Token Index: 753

Text #7

Max Range: 1.9123. Min Range: -1.9123

Max Act: 1.4789. Min Act: -0.0000

Data Index: 1985494 (The Pile)

Max Activating Token Index: 339

Text #8

Max Range: 1.9123. Min Range: -1.9123

Max Act: 1.4292. Min Act: -0.0000

Data Index: 73870 (The Pile)

Max Activating Token Index: 890

Text #9

Max Range: 1.9123. Min Range: -1.9123

Max Act: 1.4566. Min Act: -0.0000

Data Index: 1296295 (The Pile)

Max Activating Token Index: 223

Text #10

Max Range: 1.9123. Min Range: -1.9123

Max Act: 1.4352. Min Act: -0.0000

Data Index: 684988 (The Pile)

Max Activating Token Index: 499

Text #11

Max Range: 1.9123. Min Range: -1.9123

Max Act: 1.4296. Min Act: -0.0000

Data Index: 429406 (The Pile)

Max Activating Token Index: 131

Text #12

Max Range: 1.9123. Min Range: -1.9123

Max Act: 1.3973. Min Act: -0.0000

Data Index: 1678415 (The Pile)

Max Activating Token Index: 714

Text #13

Max Range: 1.9123. Min Range: -1.9123

Max Act: 1.4481. Min Act: -0.0000

Data Index: 692509 (The Pile)

Max Activating Token Index: 693

Text #14

Max Range: 1.9123. Min Range: -1.9123

Max Act: 1.3681. Min Act: -0.0000

Data Index: 405620 (The Pile)

Max Activating Token Index: 763

Text #15

Max Range: 1.9123. Min Range: -1.9123

Max Act: 1.3778. Min Act: -0.0000

Data Index: 1382770 (The Pile)

Max Activating Token Index: 753

Text #16

Max Range: 1.9123. Min Range: -1.9123

Max Act: 1.4121. Min Act: -0.0000

Data Index: 995145 (The Pile)

Max Activating Token Index: 518

Text #17

Max Range: 1.9123. Min Range: -1.9123

Max Act: 1.3549. Min Act: -0.0000

Data Index: 513770 (The Pile)

Max Activating Token Index: 212

Text #18

Max Range: 1.9123. Min Range: -1.9123

Max Act: 1.3721. Min Act: -0.0000

Data Index: 84126 (The Pile)

Max Activating Token Index: 792

Text #19

Max Range: 1.9123. Min Range: -1.9123

Max Act: 1.3568. Min Act: -0.0000

Data Index: 1453301 (The Pile)

Max Activating Token Index: 537