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

Dataset: The Pile

Neuron 1123 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: 1.2402. Min Range: -1.2402

Max Act: 1.2402. Min Act: -0.0000

Data Index: 962755 (The Pile)

Max Activating Token Index: 995

Text #1

Max Range: 1.2402. Min Range: -1.2402

Max Act: 0.9413. Min Act: -0.0000

Data Index: 376722 (The Pile)

Max Activating Token Index: 662

Text #2

Max Range: 1.2402. Min Range: -1.2402

Max Act: 1.0064. Min Act: -0.0000

Data Index: 1413376 (The Pile)

Max Activating Token Index: 771

Text #3

Max Range: 1.2402. Min Range: -1.2402

Max Act: 1.2303. Min Act: -0.0000

Data Index: 1319965 (The Pile)

Max Activating Token Index: 32

Text #4

Max Range: 1.2402. Min Range: -1.2402

Max Act: 0.9410. Min Act: -0.0000

Data Index: 458827 (The Pile)

Max Activating Token Index: 355

Text #5

Max Range: 1.2402. Min Range: -1.2402

Max Act: 0.9151. Min Act: -0.0000

Data Index: 1328295 (The Pile)

Max Activating Token Index: 676

Text #6

Max Range: 1.2402. Min Range: -1.2402

Max Act: 1.0125. Min Act: -0.0000

Data Index: 1981041 (The Pile)

Max Activating Token Index: 541

Text #7

Max Range: 1.2402. Min Range: -1.2402

Max Act: 0.8119. Min Act: -0.0000

Data Index: 245816 (The Pile)

Max Activating Token Index: 523

Text #8

Max Range: 1.2402. Min Range: -1.2402

Max Act: 0.9025. Min Act: -0.0000

Data Index: 1149100 (The Pile)

Max Activating Token Index: 346

Text #9

Max Range: 1.2402. Min Range: -1.2402

Max Act: 1.0387. Min Act: -0.0000

Data Index: 1751961 (The Pile)

Max Activating Token Index: 156

Text #10

Max Range: 1.2402. Min Range: -1.2402

Max Act: 0.9630. Min Act: -0.0000

Data Index: 1909868 (The Pile)

Max Activating Token Index: 710

Text #11

Max Range: 1.2402. Min Range: -1.2402

Max Act: 0.8780. Min Act: -0.0000

Data Index: 1738086 (The Pile)

Max Activating Token Index: 955

Text #12

Max Range: 1.2402. Min Range: -1.2402

Max Act: 0.9279. Min Act: -0.0000

Data Index: 1187320 (The Pile)

Max Activating Token Index: 470

Text #13

Max Range: 1.2402. Min Range: -1.2402

Max Act: 0.8639. Min Act: -0.0000

Data Index: 1975729 (The Pile)

Max Activating Token Index: 374

Text #14

Max Range: 1.2402. Min Range: -1.2402

Max Act: 0.7275. Min Act: -0.0000

Data Index: 974404 (The Pile)

Max Activating Token Index: 490

Text #15

Max Range: 1.2402. Min Range: -1.2402

Max Act: 0.8742. Min Act: -0.0000

Data Index: 174688 (The Pile)

Max Activating Token Index: 264

Text #16

Max Range: 1.2402. Min Range: -1.2402

Max Act: 0.7993. Min Act: -0.0000

Data Index: 1734615 (The Pile)

Max Activating Token Index: 681

Text #17

Max Range: 1.2402. Min Range: -1.2402

Max Act: 0.8102. Min Act: -0.0000

Data Index: 1730840 (The Pile)

Max Activating Token Index: 526

Text #18

Max Range: 1.2402. Min Range: -1.2402

Max Act: 0.8020. Min Act: -0.0000

Data Index: 1927266 (The Pile)

Max Activating Token Index: 424

Text #19

Max Range: 1.2402. Min Range: -1.2402

Max Act: 0.7807. Min Act: -0.0000

Data Index: 1927028 (The Pile)

Max Activating Token Index: 281