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

Dataset: The Pile

Neuron 3620 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0588. Min Range: -3.0588

Max Act: 2.8694. Min Act: -0.0000

Data Index: 612885 (The Pile)

Max Activating Token Index: 110

Text #1

Max Range: 3.0588. Min Range: -3.0588

Max Act: 3.0588. Min Act: -0.0000

Data Index: 1795955 (The Pile)

Max Activating Token Index: 80

Text #2

Max Range: 3.0588. Min Range: -3.0588

Max Act: 2.5788. Min Act: -0.0000

Data Index: 627312 (The Pile)

Max Activating Token Index: 870

Text #3

Max Range: 3.0588. Min Range: -3.0588

Max Act: 1.7906. Min Act: -0.0000

Data Index: 230460 (The Pile)

Max Activating Token Index: 868

Text #4

Max Range: 3.0588. Min Range: -3.0588

Max Act: 2.5270. Min Act: -0.0000

Data Index: 1407495 (The Pile)

Max Activating Token Index: 1014

Text #5

Max Range: 3.0588. Min Range: -3.0588

Max Act: 2.1587. Min Act: -0.0000

Data Index: 877127 (The Pile)

Max Activating Token Index: 877

Text #6

Max Range: 3.0588. Min Range: -3.0588

Max Act: 2.4380. Min Act: -0.0000

Data Index: 1594749 (The Pile)

Max Activating Token Index: 900

Text #7

Max Range: 3.0588. Min Range: -3.0588

Max Act: 2.1293. Min Act: -0.0000

Data Index: 1408108 (The Pile)

Max Activating Token Index: 995

Text #8

Max Range: 3.0588. Min Range: -3.0588

Max Act: 2.6816. Min Act: -0.0000

Data Index: 380342 (The Pile)

Max Activating Token Index: 374

Text #9

Max Range: 3.0588. Min Range: -3.0588

Max Act: 2.6321. Min Act: -0.0000

Data Index: 1482858 (The Pile)

Max Activating Token Index: 874

Text #10

Max Range: 3.0588. Min Range: -3.0588

Max Act: 2.2315. Min Act: -0.0000

Data Index: 732929 (The Pile)

Max Activating Token Index: 841

Text #11

Max Range: 3.0588. Min Range: -3.0588

Max Act: 2.3066. Min Act: -0.0000

Data Index: 1368350 (The Pile)

Max Activating Token Index: 492

Text #12

Max Range: 3.0588. Min Range: -3.0588

Max Act: 2.6960. Min Act: -0.0000

Data Index: 66014 (The Pile)

Max Activating Token Index: 802

Text #13

Max Range: 3.0588. Min Range: -3.0588

Max Act: 2.1621. Min Act: -0.0000

Data Index: 1413859 (The Pile)

Max Activating Token Index: 1010

Text #14

Max Range: 3.0588. Min Range: -3.0588

Max Act: 2.1712. Min Act: -0.0000

Data Index: 1551193 (The Pile)

Max Activating Token Index: 816

Text #15

Max Range: 3.0588. Min Range: -3.0588

Max Act: 2.2533. Min Act: -0.0000

Data Index: 290241 (The Pile)

Max Activating Token Index: 836

Text #16

Max Range: 3.0588. Min Range: -3.0588

Max Act: 2.4025. Min Act: -0.0000

Data Index: 1915067 (The Pile)

Max Activating Token Index: 643

Text #17

Max Range: 3.0588. Min Range: -3.0588

Max Act: 2.2760. Min Act: -0.0000

Data Index: 809998 (The Pile)

Max Activating Token Index: 980

Text #18

Max Range: 3.0588. Min Range: -3.0588

Max Act: 2.0644. Min Act: -0.0000

Data Index: 429658 (The Pile)

Max Activating Token Index: 1001

Text #19

Max Range: 3.0588. Min Range: -3.0588

Max Act: 1.8167. Min Act: -0.0000

Data Index: 1570588 (The Pile)

Max Activating Token Index: 996