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

Dataset: The Pile

Neuron 4204 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: 1.3830. Min Range: -1.3830

Max Act: 1.3560. Min Act: -0.0000

Data Index: 785515 (The Pile)

Max Activating Token Index: 725

Text #1

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.1493. Min Act: -0.0000

Data Index: 1034445 (The Pile)

Max Activating Token Index: 913

Text #2

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.2763. Min Act: -0.0000

Data Index: 872167 (The Pile)

Max Activating Token Index: 351

Text #3

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.2411. Min Act: -0.0000

Data Index: 200564 (The Pile)

Max Activating Token Index: 557

Text #4

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.3830. Min Act: -0.0000

Data Index: 429026 (The Pile)

Max Activating Token Index: 636

Text #5

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.1647. Min Act: -0.0000

Data Index: 113325 (The Pile)

Max Activating Token Index: 764

Text #6

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.2057. Min Act: -0.0000

Data Index: 747204 (The Pile)

Max Activating Token Index: 81

Text #7

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.1174. Min Act: -0.0000

Data Index: 1303634 (The Pile)

Max Activating Token Index: 233

Text #8

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.1888. Min Act: -0.0000

Data Index: 917681 (The Pile)

Max Activating Token Index: 258

Text #9

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.1765. Min Act: -0.0000

Data Index: 861021 (The Pile)

Max Activating Token Index: 633

Text #10

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.1848. Min Act: -0.0000

Data Index: 121377 (The Pile)

Max Activating Token Index: 245

Text #11

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.1742. Min Act: -0.0000

Data Index: 1787285 (The Pile)

Max Activating Token Index: 256

Text #12

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.1083. Min Act: -0.0000

Data Index: 1547784 (The Pile)

Max Activating Token Index: 563

Text #13

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.1717. Min Act: -0.0000

Data Index: 1368792 (The Pile)

Max Activating Token Index: 320

Text #14

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.1563. Min Act: 0.0000

Data Index: 396458 (The Pile)

Max Activating Token Index: 768

Text #15

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.0925. Min Act: -0.0000

Data Index: 563573 (The Pile)

Max Activating Token Index: 109

Text #16

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.0915. Min Act: -0.0000

Data Index: 746974 (The Pile)

Max Activating Token Index: 580

Text #17

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.2202. Min Act: -0.0000

Data Index: 565581 (The Pile)

Max Activating Token Index: 910

Text #18

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.0754. Min Act: -0.0000

Data Index: 1694070 (The Pile)

Max Activating Token Index: 95

Text #19

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.1417. Min Act: -0.0000

Data Index: 334351 (The Pile)

Max Activating Token Index: 377