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

Dataset: The Pile

Neuron 3369 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3616. Min Range: -1.3616

Max Act: 1.3616. Min Act: -0.0000

Data Index: 319991 (The Pile)

Max Activating Token Index: 849

Text #1

Max Range: 1.3616. Min Range: -1.3616

Max Act: 1.2568. Min Act: -0.0000

Data Index: 1005846 (The Pile)

Max Activating Token Index: 356

Text #2

Max Range: 1.3616. Min Range: -1.3616

Max Act: 1.1120. Min Act: -0.0000

Data Index: 1604070 (The Pile)

Max Activating Token Index: 784

Text #3

Max Range: 1.3616. Min Range: -1.3616

Max Act: 1.0423. Min Act: -0.0000

Data Index: 341395 (The Pile)

Max Activating Token Index: 65

Text #4

Max Range: 1.3616. Min Range: -1.3616

Max Act: 1.0240. Min Act: 0.0000

Data Index: 700450 (The Pile)

Max Activating Token Index: 366

Text #5

Max Range: 1.3616. Min Range: -1.3616

Max Act: 1.0108. Min Act: -0.0000

Data Index: 1211104 (The Pile)

Max Activating Token Index: 374

Text #6

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.9856. Min Act: -0.0000

Data Index: 324185 (The Pile)

Max Activating Token Index: 611

Text #7

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.9767. Min Act: -0.0000

Data Index: 1781512 (The Pile)

Max Activating Token Index: 296

Text #8

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.9613. Min Act: -0.0000

Data Index: 123816 (The Pile)

Max Activating Token Index: 492

Text #9

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.9822. Min Act: 0.0000

Data Index: 225468 (The Pile)

Max Activating Token Index: 823

Text #10

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.9190. Min Act: 0.0000

Data Index: 1997664 (The Pile)

Max Activating Token Index: 654

Text #11

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.9103. Min Act: -0.0000

Data Index: 120837 (The Pile)

Max Activating Token Index: 323

Text #12

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.9016. Min Act: 0.0000

Data Index: 1687219 (The Pile)

Max Activating Token Index: 958

Text #13

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.9009. Min Act: -0.0000

Data Index: 1906897 (The Pile)

Max Activating Token Index: 542

Text #14

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.8336. Min Act: -0.0000

Data Index: 784924 (The Pile)

Max Activating Token Index: 796

Text #15

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.8815. Min Act: -0.0000

Data Index: 1734351 (The Pile)

Max Activating Token Index: 563

Text #16

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.8413. Min Act: -0.0000

Data Index: 1534802 (The Pile)

Max Activating Token Index: 695

Text #17

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.8446. Min Act: -0.0000

Data Index: 310558 (The Pile)

Max Activating Token Index: 630

Text #18

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.8344. Min Act: -0.0000

Data Index: 1176555 (The Pile)

Max Activating Token Index: 964

Text #19

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.8788. Min Act: -0.0000

Data Index: 554398 (The Pile)

Max Activating Token Index: 405