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

Dataset: The Pile

Neuron 1118 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: 3.6840. Min Range: -3.6840

Max Act: 3.6840. Min Act: -0.0000

Data Index: 64042 (The Pile)

Max Activating Token Index: 517

Text #1

Max Range: 3.6840. Min Range: -3.6840

Max Act: 3.3965. Min Act: -0.0000

Data Index: 176153 (The Pile)

Max Activating Token Index: 553

Text #2

Max Range: 3.6840. Min Range: -3.6840

Max Act: 2.8935. Min Act: -0.0000

Data Index: 1982356 (The Pile)

Max Activating Token Index: 893

Text #3

Max Range: 3.6840. Min Range: -3.6840

Max Act: 3.0130. Min Act: -0.0000

Data Index: 1854266 (The Pile)

Max Activating Token Index: 597

Text #4

Max Range: 3.6840. Min Range: -3.6840

Max Act: 2.6046. Min Act: -0.0000

Data Index: 826924 (The Pile)

Max Activating Token Index: 539

Text #5

Max Range: 3.6840. Min Range: -3.6840

Max Act: 2.7524. Min Act: -0.0000

Data Index: 1752329 (The Pile)

Max Activating Token Index: 427

Text #6

Max Range: 3.6840. Min Range: -3.6840

Max Act: 2.5934. Min Act: -0.0000

Data Index: 755359 (The Pile)

Max Activating Token Index: 929

Text #7

Max Range: 3.6840. Min Range: -3.6840

Max Act: 3.0126. Min Act: -0.0000

Data Index: 1765100 (The Pile)

Max Activating Token Index: 709

Text #8

Max Range: 3.6840. Min Range: -3.6840

Max Act: 2.9558. Min Act: -0.0000

Data Index: 1368017 (The Pile)

Max Activating Token Index: 797

Text #9

Max Range: 3.6840. Min Range: -3.6840

Max Act: 2.7560. Min Act: -0.0000

Data Index: 228776 (The Pile)

Max Activating Token Index: 202

Text #10

Max Range: 3.6840. Min Range: -3.6840

Max Act: 2.7560. Min Act: -0.0000

Data Index: 338846 (The Pile)

Max Activating Token Index: 256

Text #11

Max Range: 3.6840. Min Range: -3.6840

Max Act: 2.7421. Min Act: -0.0000

Data Index: 1940859 (The Pile)

Max Activating Token Index: 199

Text #12

Max Range: 3.6840. Min Range: -3.6840

Max Act: 2.5729. Min Act: -0.0000

Data Index: 1606612 (The Pile)

Max Activating Token Index: 238

Text #13

Max Range: 3.6840. Min Range: -3.6840

Max Act: 2.6571. Min Act: -0.0000

Data Index: 636968 (The Pile)

Max Activating Token Index: 857

Text #14

Max Range: 3.6840. Min Range: -3.6840

Max Act: 2.6475. Min Act: -0.0000

Data Index: 1888904 (The Pile)

Max Activating Token Index: 548

Text #15

Max Range: 3.6840. Min Range: -3.6840

Max Act: 2.6190. Min Act: -0.0000

Data Index: 215017 (The Pile)

Max Activating Token Index: 1010

Text #16

Max Range: 3.6840. Min Range: -3.6840

Max Act: 2.9481. Min Act: -0.0000

Data Index: 518708 (The Pile)

Max Activating Token Index: 675

Text #17

Max Range: 3.6840. Min Range: -3.6840

Max Act: 2.6281. Min Act: -0.0000

Data Index: 915321 (The Pile)

Max Activating Token Index: 535

Text #18

Max Range: 3.6840. Min Range: -3.6840

Max Act: 2.5985. Min Act: -0.0000

Data Index: 679901 (The Pile)

Max Activating Token Index: 592

Text #19

Max Range: 3.6840. Min Range: -3.6840

Max Act: 2.4262. Min Act: -0.0000

Data Index: 818590 (The Pile)

Max Activating Token Index: 484