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

Dataset: The Pile

Neuron 3796 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.6556. Min Act: -0.0000

Data Index: 28229 (The Pile)

Max Activating Token Index: 546

Text #1

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.6018. Min Act: -0.0000

Data Index: 1906838 (The Pile)

Max Activating Token Index: 596

Text #2

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.6010. Min Act: -0.0000

Data Index: 5281 (The Pile)

Max Activating Token Index: 582

Text #3

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.5963. Min Act: -0.0000

Data Index: 1269120 (The Pile)

Max Activating Token Index: 908

Text #4

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.6075. Min Act: -0.0000

Data Index: 1289412 (The Pile)

Max Activating Token Index: 498

Text #5

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.6195. Min Act: -0.0000

Data Index: 663256 (The Pile)

Max Activating Token Index: 927

Text #6

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.5847. Min Act: -0.0000

Data Index: 901646 (The Pile)

Max Activating Token Index: 602

Text #7

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.5916. Min Act: -0.0000

Data Index: 266374 (The Pile)

Max Activating Token Index: 21

Text #8

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.5882. Min Act: -0.0000

Data Index: 920384 (The Pile)

Max Activating Token Index: 482

Text #9

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.6257. Min Act: -0.0000

Data Index: 1711526 (The Pile)

Max Activating Token Index: 379

Text #10

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.5852. Min Act: -0.0000

Data Index: 934804 (The Pile)

Max Activating Token Index: 565

Text #11

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.5853. Min Act: -0.0000

Data Index: 86953 (The Pile)

Max Activating Token Index: 366

Text #12

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.5746. Min Act: -0.0000

Data Index: 1076780 (The Pile)

Max Activating Token Index: 809

Text #13

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.5538. Min Act: -0.0000

Data Index: 1173443 (The Pile)

Max Activating Token Index: 438

Text #14

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.5875. Min Act: -0.0000

Data Index: 1752081 (The Pile)

Max Activating Token Index: 348

Text #15

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.5928. Min Act: -0.0000

Data Index: 139983 (The Pile)

Max Activating Token Index: 921

Text #16

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.5323. Min Act: -0.0000

Data Index: 1088600 (The Pile)

Max Activating Token Index: 239

Text #17

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.5605. Min Act: -0.0000

Data Index: 1455628 (The Pile)

Max Activating Token Index: 928

Text #18

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.5399. Min Act: -0.0000

Data Index: 1750395 (The Pile)

Max Activating Token Index: 461

Text #19

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.5563. Min Act: -0.0000

Data Index: 1319017 (The Pile)

Max Activating Token Index: 985