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

Dataset: The Pile

Neuron 2707 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: 1.9725. Min Range: -1.9725

Max Act: 1.9725. Min Act: -0.0000

Data Index: 514758 (The Pile)

Max Activating Token Index: 726

Text #1

Max Range: 1.9725. Min Range: -1.9725

Max Act: 1.7446. Min Act: -0.0000

Data Index: 188832 (The Pile)

Max Activating Token Index: 878

Text #2

Max Range: 1.9725. Min Range: -1.9725

Max Act: 1.3506. Min Act: -0.0000

Data Index: 748358 (The Pile)

Max Activating Token Index: 684

Text #3

Max Range: 1.9725. Min Range: -1.9725

Max Act: 1.3112. Min Act: -0.0000

Data Index: 1234485 (The Pile)

Max Activating Token Index: 771

Text #4

Max Range: 1.9725. Min Range: -1.9725

Max Act: 1.2481. Min Act: -0.0000

Data Index: 1638248 (The Pile)

Max Activating Token Index: 389

Text #5

Max Range: 1.9725. Min Range: -1.9725

Max Act: 1.1314. Min Act: -0.0000

Data Index: 1843834 (The Pile)

Max Activating Token Index: 324

Text #6

Max Range: 1.9725. Min Range: -1.9725

Max Act: 1.1938. Min Act: -0.0000

Data Index: 1684127 (The Pile)

Max Activating Token Index: 329

Text #7

Max Range: 1.9725. Min Range: -1.9725

Max Act: 1.1564. Min Act: -0.0000

Data Index: 152391 (The Pile)

Max Activating Token Index: 515

Text #8

Max Range: 1.9725. Min Range: -1.9725

Max Act: 0.8861. Min Act: -0.0000

Data Index: 1647503 (The Pile)

Max Activating Token Index: 985

Text #9

Max Range: 1.9725. Min Range: -1.9725

Max Act: 1.1781. Min Act: -0.0000

Data Index: 252122 (The Pile)

Max Activating Token Index: 731

Text #10

Max Range: 1.9725. Min Range: -1.9725

Max Act: 1.0632. Min Act: -0.0000

Data Index: 67576 (The Pile)

Max Activating Token Index: 45

Text #11

Max Range: 1.9725. Min Range: -1.9725

Max Act: 0.9909. Min Act: -0.0000

Data Index: 1569713 (The Pile)

Max Activating Token Index: 493

Text #12

Max Range: 1.9725. Min Range: -1.9725

Max Act: 0.9892. Min Act: -0.0000

Data Index: 1495616 (The Pile)

Max Activating Token Index: 919

Text #13

Max Range: 1.9725. Min Range: -1.9725

Max Act: 1.0539. Min Act: -0.0000

Data Index: 1740743 (The Pile)

Max Activating Token Index: 469

Text #14

Max Range: 1.9725. Min Range: -1.9725

Max Act: 1.0187. Min Act: -0.0000

Data Index: 415442 (The Pile)

Max Activating Token Index: 688

Text #15

Max Range: 1.9725. Min Range: -1.9725

Max Act: 1.0168. Min Act: -0.0000

Data Index: 235298 (The Pile)

Max Activating Token Index: 329

Text #16

Max Range: 1.9725. Min Range: -1.9725

Max Act: 0.9290. Min Act: -0.0000

Data Index: 1349187 (The Pile)

Max Activating Token Index: 47

Text #17

Max Range: 1.9725. Min Range: -1.9725

Max Act: 0.9848. Min Act: -0.0000

Data Index: 1097361 (The Pile)

Max Activating Token Index: 130

Text #18

Max Range: 1.9725. Min Range: -1.9725

Max Act: 0.9761. Min Act: -0.0000

Data Index: 443879 (The Pile)

Max Activating Token Index: 425

Text #19

Max Range: 1.9725. Min Range: -1.9725

Max Act: 0.9166. Min Act: -0.0000

Data Index: 188237 (The Pile)

Max Activating Token Index: 655