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

Dataset: The Pile

Neuron 1517 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5402. Min Range: -3.5402

Max Act: 3.4702. Min Act: -0.0000

Data Index: 18960 (The Pile)

Max Activating Token Index: 1003

Text #1

Max Range: 3.5402. Min Range: -3.5402

Max Act: 3.5402. Min Act: -0.0000

Data Index: 1749687 (The Pile)

Max Activating Token Index: 803

Text #2

Max Range: 3.5402. Min Range: -3.5402

Max Act: 3.1763. Min Act: -0.0000

Data Index: 1169264 (The Pile)

Max Activating Token Index: 330

Text #3

Max Range: 3.5402. Min Range: -3.5402

Max Act: 3.3208. Min Act: -0.0000

Data Index: 1273147 (The Pile)

Max Activating Token Index: 631

Text #4

Max Range: 3.5402. Min Range: -3.5402

Max Act: 2.9503. Min Act: -0.0000

Data Index: 506305 (The Pile)

Max Activating Token Index: 510

Text #5

Max Range: 3.5402. Min Range: -3.5402

Max Act: 3.0201. Min Act: -0.0000

Data Index: 832243 (The Pile)

Max Activating Token Index: 371

Text #6

Max Range: 3.5402. Min Range: -3.5402

Max Act: 2.8351. Min Act: -0.0000

Data Index: 239251 (The Pile)

Max Activating Token Index: 915

Text #7

Max Range: 3.5402. Min Range: -3.5402

Max Act: 3.1123. Min Act: -0.0000

Data Index: 1374244 (The Pile)

Max Activating Token Index: 854

Text #8

Max Range: 3.5402. Min Range: -3.5402

Max Act: 3.1645. Min Act: -0.0000

Data Index: 1105884 (The Pile)

Max Activating Token Index: 835

Text #9

Max Range: 3.5402. Min Range: -3.5402

Max Act: 2.6976. Min Act: -0.0000

Data Index: 1542607 (The Pile)

Max Activating Token Index: 788

Text #10

Max Range: 3.5402. Min Range: -3.5402

Max Act: 2.6055. Min Act: -0.0000

Data Index: 1139809 (The Pile)

Max Activating Token Index: 881

Text #11

Max Range: 3.5402. Min Range: -3.5402

Max Act: 2.6745. Min Act: -0.0000

Data Index: 1891861 (The Pile)

Max Activating Token Index: 662

Text #12

Max Range: 3.5402. Min Range: -3.5402

Max Act: 2.5468. Min Act: -0.0000

Data Index: 1971152 (The Pile)

Max Activating Token Index: 744

Text #13

Max Range: 3.5402. Min Range: -3.5402

Max Act: 2.8623. Min Act: -0.0000

Data Index: 1467662 (The Pile)

Max Activating Token Index: 767

Text #14

Max Range: 3.5402. Min Range: -3.5402

Max Act: 2.3647. Min Act: -0.0000

Data Index: 1805079 (The Pile)

Max Activating Token Index: 836

Text #15

Max Range: 3.5402. Min Range: -3.5402

Max Act: 2.5996. Min Act: -0.0000

Data Index: 1205013 (The Pile)

Max Activating Token Index: 476

Text #16

Max Range: 3.5402. Min Range: -3.5402

Max Act: 2.5499. Min Act: -0.0000

Data Index: 1131188 (The Pile)

Max Activating Token Index: 476

Text #17

Max Range: 3.5402. Min Range: -3.5402

Max Act: 2.5300. Min Act: -0.0000

Data Index: 1875629 (The Pile)

Max Activating Token Index: 764

Text #18

Max Range: 3.5402. Min Range: -3.5402

Max Act: 2.6453. Min Act: -0.0000

Data Index: 924844 (The Pile)

Max Activating Token Index: 910

Text #19

Max Range: 3.5402. Min Range: -3.5402

Max Act: 2.6588. Min Act: -0.0000

Data Index: 1196932 (The Pile)

Max Activating Token Index: 494