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

Dataset: The Pile

Neuron 23 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: 3.4695. Min Range: -3.4695

Max Act: 3.4695. Min Act: -0.0000

Data Index: 1020850 (The Pile)

Max Activating Token Index: 487

Text #1

Max Range: 3.4695. Min Range: -3.4695

Max Act: 3.2320. Min Act: -0.0000

Data Index: 920373 (The Pile)

Max Activating Token Index: 19

Text #2

Max Range: 3.4695. Min Range: -3.4695

Max Act: 2.4425. Min Act: -0.0000

Data Index: 385973 (The Pile)

Max Activating Token Index: 4

Text #3

Max Range: 3.4695. Min Range: -3.4695

Max Act: 2.2560. Min Act: -0.0000

Data Index: 743481 (The Pile)

Max Activating Token Index: 44

Text #4

Max Range: 3.4695. Min Range: -3.4695

Max Act: 2.2539. Min Act: -0.0000

Data Index: 1630229 (The Pile)

Max Activating Token Index: 487

Text #5

Max Range: 3.4695. Min Range: -3.4695

Max Act: 2.1345. Min Act: -0.0000

Data Index: 1388226 (The Pile)

Max Activating Token Index: 816

Text #6

Max Range: 3.4695. Min Range: -3.4695

Max Act: 2.2228. Min Act: -0.0000

Data Index: 137164 (The Pile)

Max Activating Token Index: 397

Text #7

Max Range: 3.4695. Min Range: -3.4695

Max Act: 1.8938. Min Act: -0.0000

Data Index: 854817 (The Pile)

Max Activating Token Index: 708

Text #8

Max Range: 3.4695. Min Range: -3.4695

Max Act: 1.7509. Min Act: -0.0000

Data Index: 1811580 (The Pile)

Max Activating Token Index: 899

Text #9

Max Range: 3.4695. Min Range: -3.4695

Max Act: 2.0526. Min Act: -0.0000

Data Index: 1477360 (The Pile)

Max Activating Token Index: 13

Text #10

Max Range: 3.4695. Min Range: -3.4695

Max Act: 1.9276. Min Act: -0.0000

Data Index: 1847017 (The Pile)

Max Activating Token Index: 773

Text #11

Max Range: 3.4695. Min Range: -3.4695

Max Act: 2.0336. Min Act: -0.0000

Data Index: 1982020 (The Pile)

Max Activating Token Index: 725

Text #12

Max Range: 3.4695. Min Range: -3.4695

Max Act: 1.8970. Min Act: -0.0000

Data Index: 1801122 (The Pile)

Max Activating Token Index: 400

Text #13

Max Range: 3.4695. Min Range: -3.4695

Max Act: 1.9532. Min Act: -0.0000

Data Index: 579866 (The Pile)

Max Activating Token Index: 226

Text #14

Max Range: 3.4695. Min Range: -3.4695

Max Act: 1.9201. Min Act: -0.0000

Data Index: 1499389 (The Pile)

Max Activating Token Index: 769

Text #15

Max Range: 3.4695. Min Range: -3.4695

Max Act: 1.7967. Min Act: -0.0000

Data Index: 1574586 (The Pile)

Max Activating Token Index: 811

Text #16

Max Range: 3.4695. Min Range: -3.4695

Max Act: 2.0737. Min Act: -0.0000

Data Index: 348907 (The Pile)

Max Activating Token Index: 735

Text #17

Max Range: 3.4695. Min Range: -3.4695

Max Act: 1.7915. Min Act: -0.0000

Data Index: 1155776 (The Pile)

Max Activating Token Index: 604

Text #18

Max Range: 3.4695. Min Range: -3.4695

Max Act: 1.7831. Min Act: -0.0000

Data Index: 1335438 (The Pile)

Max Activating Token Index: 915

Text #19

Max Range: 3.4695. Min Range: -3.4695

Max Act: 1.7954. Min Act: -0.0000

Data Index: 257260 (The Pile)

Max Activating Token Index: 739