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

Dataset: The Pile

Neuron 2251 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: 1.6033. Min Range: -1.6033

Max Act: 1.5139. Min Act: -0.0000

Data Index: 1174155 (The Pile)

Max Activating Token Index: 678

Text #1

Max Range: 1.6033. Min Range: -1.6033

Max Act: 1.6033. Min Act: -0.0000

Data Index: 1313540 (The Pile)

Max Activating Token Index: 93

Text #2

Max Range: 1.6033. Min Range: -1.6033

Max Act: 1.4271. Min Act: -0.0000

Data Index: 849564 (The Pile)

Max Activating Token Index: 494

Text #3

Max Range: 1.6033. Min Range: -1.6033

Max Act: 1.5679. Min Act: -0.0000

Data Index: 1213000 (The Pile)

Max Activating Token Index: 552

Text #4

Max Range: 1.6033. Min Range: -1.6033

Max Act: 1.3889. Min Act: -0.0000

Data Index: 204412 (The Pile)

Max Activating Token Index: 666

Text #5

Max Range: 1.6033. Min Range: -1.6033

Max Act: 1.3500. Min Act: -0.0000

Data Index: 1234841 (The Pile)

Max Activating Token Index: 783

Text #6

Max Range: 1.6033. Min Range: -1.6033

Max Act: 1.3500. Min Act: -0.0000

Data Index: 1770942 (The Pile)

Max Activating Token Index: 643

Text #7

Max Range: 1.6033. Min Range: -1.6033

Max Act: 1.3382. Min Act: -0.0000

Data Index: 1166429 (The Pile)

Max Activating Token Index: 364

Text #8

Max Range: 1.6033. Min Range: -1.6033

Max Act: 1.2431. Min Act: -0.0000

Data Index: 720460 (The Pile)

Max Activating Token Index: 840

Text #9

Max Range: 1.6033. Min Range: -1.6033

Max Act: 1.3083. Min Act: -0.0000

Data Index: 1097793 (The Pile)

Max Activating Token Index: 154

Text #10

Max Range: 1.6033. Min Range: -1.6033

Max Act: 1.2116. Min Act: -0.0000

Data Index: 1121451 (The Pile)

Max Activating Token Index: 59

Text #11

Max Range: 1.6033. Min Range: -1.6033

Max Act: 1.3473. Min Act: -0.0000

Data Index: 1892298 (The Pile)

Max Activating Token Index: 166

Text #12

Max Range: 1.6033. Min Range: -1.6033

Max Act: 1.2464. Min Act: -0.0000

Data Index: 1585146 (The Pile)

Max Activating Token Index: 784

Text #13

Max Range: 1.6033. Min Range: -1.6033

Max Act: 1.2558. Min Act: -0.0000

Data Index: 1685120 (The Pile)

Max Activating Token Index: 935

Text #14

Max Range: 1.6033. Min Range: -1.6033

Max Act: 1.1730. Min Act: -0.0000

Data Index: 1610297 (The Pile)

Max Activating Token Index: 168

Text #15

Max Range: 1.6033. Min Range: -1.6033

Max Act: 1.3059. Min Act: -0.0000

Data Index: 39908 (The Pile)

Max Activating Token Index: 82

Text #16

Max Range: 1.6033. Min Range: -1.6033

Max Act: 1.1491. Min Act: -0.0000

Data Index: 467930 (The Pile)

Max Activating Token Index: 973

Text #17

Max Range: 1.6033. Min Range: -1.6033

Max Act: 1.2123. Min Act: -0.0000

Data Index: 1366641 (The Pile)

Max Activating Token Index: 507

Text #18

Max Range: 1.6033. Min Range: -1.6033

Max Act: 1.1509. Min Act: -0.0000

Data Index: 1706919 (The Pile)

Max Activating Token Index: 697

Text #19

Max Range: 1.6033. Min Range: -1.6033

Max Act: 1.1425. Min Act: -0.0000

Data Index: 213439 (The Pile)

Max Activating Token Index: 658