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

Dataset: The Pile

Neuron 2112 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: 0.8490. Min Range: -0.8490

Max Act: 0.8490. Min Act: -0.0000

Data Index: 1449385 (The Pile)

Max Activating Token Index: 130

Text #1

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.7001. Min Act: -0.0000

Data Index: 1928152 (The Pile)

Max Activating Token Index: 262

Text #2

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.7284. Min Act: -0.0000

Data Index: 797892 (The Pile)

Max Activating Token Index: 504

Text #3

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.6849. Min Act: -0.0000

Data Index: 1130793 (The Pile)

Max Activating Token Index: 481

Text #4

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.6381. Min Act: -0.0000

Data Index: 491431 (The Pile)

Max Activating Token Index: 822

Text #5

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.6671. Min Act: -0.0000

Data Index: 1520164 (The Pile)

Max Activating Token Index: 175

Text #6

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.6005. Min Act: -0.0000

Data Index: 268742 (The Pile)

Max Activating Token Index: 138

Text #7

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.6456. Min Act: -0.0000

Data Index: 1755419 (The Pile)

Max Activating Token Index: 894

Text #8

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.5652. Min Act: -0.0000

Data Index: 973321 (The Pile)

Max Activating Token Index: 383

Text #9

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.6719. Min Act: -0.0000

Data Index: 891910 (The Pile)

Max Activating Token Index: 400

Text #10

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.5979. Min Act: -0.0000

Data Index: 757798 (The Pile)

Max Activating Token Index: 678

Text #11

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.5907. Min Act: -0.0000

Data Index: 76647 (The Pile)

Max Activating Token Index: 260

Text #12

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.5988. Min Act: -0.0000

Data Index: 1193630 (The Pile)

Max Activating Token Index: 436

Text #13

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.6714. Min Act: -0.0000

Data Index: 1642613 (The Pile)

Max Activating Token Index: 288

Text #14

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.5046. Min Act: -0.0000

Data Index: 1630292 (The Pile)

Max Activating Token Index: 699

Text #15

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.6340. Min Act: -0.0000

Data Index: 470611 (The Pile)

Max Activating Token Index: 419

Text #16

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.6290. Min Act: -0.0000

Data Index: 641102 (The Pile)

Max Activating Token Index: 955

Text #17

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.6188. Min Act: -0.0000

Data Index: 593389 (The Pile)

Max Activating Token Index: 156

Text #18

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.5832. Min Act: -0.0000

Data Index: 1740773 (The Pile)

Max Activating Token Index: 787

Text #19

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.5745. Min Act: -0.0000

Data Index: 667420 (The Pile)

Max Activating Token Index: 224