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

Dataset: The Pile

Neuron 3873 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: 0.3532. Min Range: -0.3532

Max Act: 0.3532. Min Act: -0.0000

Data Index: 712804 (The Pile)

Max Activating Token Index: 307

Text #1

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.3190. Min Act: -0.0000

Data Index: 1852132 (The Pile)

Max Activating Token Index: 994

Text #2

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2677. Min Act: -0.0000

Data Index: 1903464 (The Pile)

Max Activating Token Index: 302

Text #3

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2413. Min Act: -0.0000

Data Index: 1530804 (The Pile)

Max Activating Token Index: 908

Text #4

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2266. Min Act: -0.0000

Data Index: 112085 (The Pile)

Max Activating Token Index: 279

Text #5

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2467. Min Act: -0.0000

Data Index: 757593 (The Pile)

Max Activating Token Index: 540

Text #6

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.1815. Min Act: -0.0000

Data Index: 1524488 (The Pile)

Max Activating Token Index: 961

Text #7

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2103. Min Act: -0.0000

Data Index: 228698 (The Pile)

Max Activating Token Index: 535

Text #8

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.1994. Min Act: -0.0000

Data Index: 1709587 (The Pile)

Max Activating Token Index: 735

Text #9

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.1812. Min Act: -0.0000

Data Index: 781607 (The Pile)

Max Activating Token Index: 558

Text #10

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2144. Min Act: -0.0000

Data Index: 1540313 (The Pile)

Max Activating Token Index: 264

Text #11

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.1923. Min Act: -0.0000

Data Index: 716682 (The Pile)

Max Activating Token Index: 824

Text #12

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2055. Min Act: -0.0000

Data Index: 1547881 (The Pile)

Max Activating Token Index: 76

Text #13

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.1804. Min Act: -0.0000

Data Index: 558594 (The Pile)

Max Activating Token Index: 294

Text #14

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.1844. Min Act: -0.0000

Data Index: 1004180 (The Pile)

Max Activating Token Index: 549

Text #15

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.1822. Min Act: -0.0000

Data Index: 716753 (The Pile)

Max Activating Token Index: 109

Text #16

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.1939. Min Act: -0.0000

Data Index: 1640271 (The Pile)

Max Activating Token Index: 463

Text #17

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2003. Min Act: -0.0000

Data Index: 1463798 (The Pile)

Max Activating Token Index: 775

Text #18

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.1850. Min Act: -0.0000

Data Index: 105949 (The Pile)

Max Activating Token Index: 666

Text #19

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.1975. Min Act: -0.0000

Data Index: 1934577 (The Pile)

Max Activating Token Index: 204