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

Dataset: The Pile

Neuron 5116 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: 0.5590. Min Range: -0.5590

Max Act: 0.5590. Min Act: -0.0000

Data Index: 51421 (The Pile)

Max Activating Token Index: 147

Text #1

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4474. Min Act: -0.0000

Data Index: 72243 (The Pile)

Max Activating Token Index: 692

Text #2

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4438. Min Act: -0.0000

Data Index: 999392 (The Pile)

Max Activating Token Index: 946

Text #3

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4123. Min Act: -0.0000

Data Index: 1157979 (The Pile)

Max Activating Token Index: 621

Text #4

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4285. Min Act: -0.0000

Data Index: 1882205 (The Pile)

Max Activating Token Index: 31

Text #5

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3856. Min Act: -0.0000

Data Index: 926083 (The Pile)

Max Activating Token Index: 760

Text #6

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4067. Min Act: -0.0000

Data Index: 11754 (The Pile)

Max Activating Token Index: 355

Text #7

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3892. Min Act: -0.0000

Data Index: 1213635 (The Pile)

Max Activating Token Index: 779

Text #8

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4024. Min Act: -0.0000

Data Index: 251726 (The Pile)

Max Activating Token Index: 678

Text #9

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4008. Min Act: -0.0000

Data Index: 1233816 (The Pile)

Max Activating Token Index: 254

Text #10

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4400. Min Act: -0.0000

Data Index: 140096 (The Pile)

Max Activating Token Index: 547

Text #11

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4346. Min Act: -0.0000

Data Index: 1559331 (The Pile)

Max Activating Token Index: 924

Text #12

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4074. Min Act: -0.0000

Data Index: 1134015 (The Pile)

Max Activating Token Index: 526

Text #13

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4200. Min Act: -0.0000

Data Index: 111500 (The Pile)

Max Activating Token Index: 902

Text #14

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3921. Min Act: -0.0000

Data Index: 1992606 (The Pile)

Max Activating Token Index: 597

Text #15

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3879. Min Act: -0.0000

Data Index: 1591934 (The Pile)

Max Activating Token Index: 827

Text #16

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3741. Min Act: -0.0000

Data Index: 1598101 (The Pile)

Max Activating Token Index: 205

Text #17

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4250. Min Act: -0.0000

Data Index: 1744109 (The Pile)

Max Activating Token Index: 946

Text #18

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4209. Min Act: -0.0000

Data Index: 1997211 (The Pile)

Max Activating Token Index: 563

Text #19

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3628. Min Act: -0.0000

Data Index: 1552539 (The Pile)

Max Activating Token Index: 480