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

Dataset: The Pile

Neuron 3299 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4717. Min Range: -1.4717

Max Act: 1.4717. Min Act: -0.0000

Data Index: 165359 (The Pile)

Max Activating Token Index: 573

Text #1

Max Range: 1.4717. Min Range: -1.4717

Max Act: 1.2785. Min Act: -0.0000

Data Index: 765559 (The Pile)

Max Activating Token Index: 817

Text #2

Max Range: 1.4717. Min Range: -1.4717

Max Act: 1.2275. Min Act: -0.0000

Data Index: 1589769 (The Pile)

Max Activating Token Index: 407

Text #3

Max Range: 1.4717. Min Range: -1.4717

Max Act: 1.1243. Min Act: -0.0000

Data Index: 1932976 (The Pile)

Max Activating Token Index: 196

Text #4

Max Range: 1.4717. Min Range: -1.4717

Max Act: 1.1059. Min Act: -0.0000

Data Index: 789772 (The Pile)

Max Activating Token Index: 336

Text #5

Max Range: 1.4717. Min Range: -1.4717

Max Act: 1.0357. Min Act: -0.0000

Data Index: 1283031 (The Pile)

Max Activating Token Index: 634

Text #6

Max Range: 1.4717. Min Range: -1.4717

Max Act: 1.0708. Min Act: -0.0000

Data Index: 1906109 (The Pile)

Max Activating Token Index: 197

Text #7

Max Range: 1.4717. Min Range: -1.4717

Max Act: 1.0270. Min Act: -0.0000

Data Index: 1537998 (The Pile)

Max Activating Token Index: 353

Text #8

Max Range: 1.4717. Min Range: -1.4717

Max Act: 0.9591. Min Act: -0.0000

Data Index: 1914084 (The Pile)

Max Activating Token Index: 118

Text #9

Max Range: 1.4717. Min Range: -1.4717

Max Act: 1.0000. Min Act: -0.0000

Data Index: 204647 (The Pile)

Max Activating Token Index: 492

Text #10

Max Range: 1.4717. Min Range: -1.4717

Max Act: 1.0364. Min Act: 0.0000

Data Index: 950853 (The Pile)

Max Activating Token Index: 755

Text #11

Max Range: 1.4717. Min Range: -1.4717

Max Act: 1.0427. Min Act: -0.0000

Data Index: 1623985 (The Pile)

Max Activating Token Index: 602

Text #12

Max Range: 1.4717. Min Range: -1.4717

Max Act: 1.0259. Min Act: -0.0000

Data Index: 378658 (The Pile)

Max Activating Token Index: 79

Text #13

Max Range: 1.4717. Min Range: -1.4717

Max Act: 0.9254. Min Act: -0.0000

Data Index: 1731329 (The Pile)

Max Activating Token Index: 678

Text #14

Max Range: 1.4717. Min Range: -1.4717

Max Act: 0.9870. Min Act: -0.0000

Data Index: 342637 (The Pile)

Max Activating Token Index: 293

Text #15

Max Range: 1.4717. Min Range: -1.4717

Max Act: 0.9727. Min Act: -0.0000

Data Index: 1621711 (The Pile)

Max Activating Token Index: 203

Text #16

Max Range: 1.4717. Min Range: -1.4717

Max Act: 0.9682. Min Act: -0.0000

Data Index: 1527776 (The Pile)

Max Activating Token Index: 354

Text #17

Max Range: 1.4717. Min Range: -1.4717

Max Act: 0.9718. Min Act: -0.0000

Data Index: 955057 (The Pile)

Max Activating Token Index: 706

Text #18

Max Range: 1.4717. Min Range: -1.4717

Max Act: 0.8976. Min Act: -0.0000

Data Index: 1530378 (The Pile)

Max Activating Token Index: 76

Text #19

Max Range: 1.4717. Min Range: -1.4717

Max Act: 0.9598. Min Act: -0.0000

Data Index: 1356024 (The Pile)

Max Activating Token Index: 294