Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 444 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.6364. Min Range: -3.6364

Max Act: 3.6364. Min Act: -0.0000

Data Index: 1030613 (The Pile)

Max Activating Token Index: 465

Text #1

Max Range: 3.6364. Min Range: -3.6364

Max Act: 1.2799. Min Act: -0.0000

Data Index: 1717178 (The Pile)

Max Activating Token Index: 113

Text #2

Max Range: 3.6364. Min Range: -3.6364

Max Act: 1.9657. Min Act: -0.0000

Data Index: 324695 (The Pile)

Max Activating Token Index: 761

Text #3

Max Range: 3.6364. Min Range: -3.6364

Max Act: 2.3255. Min Act: -0.0000

Data Index: 1813146 (The Pile)

Max Activating Token Index: 798

Text #4

Max Range: 3.6364. Min Range: -3.6364

Max Act: 2.6181. Min Act: -0.0000

Data Index: 1331995 (The Pile)

Max Activating Token Index: 579

Text #5

Max Range: 3.6364. Min Range: -3.6364

Max Act: 1.9657. Min Act: -0.0000

Data Index: 1553229 (The Pile)

Max Activating Token Index: 716

Text #6

Max Range: 3.6364. Min Range: -3.6364

Max Act: 1.9186. Min Act: -0.0000

Data Index: 495782 (The Pile)

Max Activating Token Index: 123

Text #7

Max Range: 3.6364. Min Range: -3.6364

Max Act: 0.9992. Min Act: -0.0000

Data Index: 1364405 (The Pile)

Max Activating Token Index: 473

Text #8

Max Range: 3.6364. Min Range: -3.6364

Max Act: 0.4811. Min Act: -0.0000

Data Index: 419302 (The Pile)

Max Activating Token Index: 848

Text #9

Max Range: 3.6364. Min Range: -3.6364

Max Act: 1.0432. Min Act: -0.0000

Data Index: 1227253 (The Pile)

Max Activating Token Index: 737

Text #10

Max Range: 3.6364. Min Range: -3.6364

Max Act: 0.6522. Min Act: -0.0000

Data Index: 1453255 (The Pile)

Max Activating Token Index: 574

Text #11

Max Range: 3.6364. Min Range: -3.6364

Max Act: 1.1504. Min Act: -0.0000

Data Index: 1321071 (The Pile)

Max Activating Token Index: 78

Text #12

Max Range: 3.6364. Min Range: -3.6364

Max Act: 0.9688. Min Act: -0.0000

Data Index: 277617 (The Pile)

Max Activating Token Index: 322

Text #13

Max Range: 3.6364. Min Range: -3.6364

Max Act: 0.2134. Min Act: -0.0000

Data Index: 819290 (The Pile)

Max Activating Token Index: 696

Text #14

Max Range: 3.6364. Min Range: -3.6364

Max Act: 0.9899. Min Act: -0.0000

Data Index: 1724194 (The Pile)

Max Activating Token Index: 74

Text #15

Max Range: 3.6364. Min Range: -3.6364

Max Act: 0.6668. Min Act: -0.0000

Data Index: 1005910 (The Pile)

Max Activating Token Index: 114

Text #16

Max Range: 3.6364. Min Range: -3.6364

Max Act: 0.7317. Min Act: -0.0000

Data Index: 1075761 (The Pile)

Max Activating Token Index: 556

Text #17

Max Range: 3.6364. Min Range: -3.6364

Max Act: 0.6789. Min Act: -0.0000

Data Index: 1148444 (The Pile)

Max Activating Token Index: 277

Text #18

Max Range: 3.6364. Min Range: -3.6364

Max Act: 1.4086. Min Act: -0.0000

Data Index: 1353370 (The Pile)

Max Activating Token Index: 769

Text #19

Max Range: 3.6364. Min Range: -3.6364

Max Act: 1.1443. Min Act: -0.0000

Data Index: 934307 (The Pile)

Max Activating Token Index: 32