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

Dataset: The Pile

Neuron 1006 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: 1.8621. Min Range: -1.8621

Max Act: 1.8621. Min Act: -0.0000

Data Index: 1126050 (The Pile)

Max Activating Token Index: 404

Text #1

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.6551. Min Act: -0.0000

Data Index: 1328728 (The Pile)

Max Activating Token Index: 747

Text #2

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.6034. Min Act: -0.0000

Data Index: 10687 (The Pile)

Max Activating Token Index: 337

Text #3

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.5902. Min Act: -0.0000

Data Index: 534279 (The Pile)

Max Activating Token Index: 132

Text #4

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.5633. Min Act: -0.0000

Data Index: 220148 (The Pile)

Max Activating Token Index: 425

Text #5

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.6366. Min Act: -0.0000

Data Index: 1448033 (The Pile)

Max Activating Token Index: 241

Text #6

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.4778. Min Act: -0.0000

Data Index: 882658 (The Pile)

Max Activating Token Index: 583

Text #7

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.4737. Min Act: -0.0000

Data Index: 1627266 (The Pile)

Max Activating Token Index: 329

Text #8

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.5535. Min Act: -0.0000

Data Index: 1444451 (The Pile)

Max Activating Token Index: 237

Text #9

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.3889. Min Act: -0.0000

Data Index: 506048 (The Pile)

Max Activating Token Index: 306

Text #10

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.5350. Min Act: -0.0000

Data Index: 1162037 (The Pile)

Max Activating Token Index: 278

Text #11

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.5277. Min Act: -0.0000

Data Index: 851 (The Pile)

Max Activating Token Index: 664

Text #12

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.5176. Min Act: -0.0000

Data Index: 1771087 (The Pile)

Max Activating Token Index: 211

Text #13

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.5914. Min Act: -0.0000

Data Index: 355824 (The Pile)

Max Activating Token Index: 496

Text #14

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.4217. Min Act: -0.0000

Data Index: 401907 (The Pile)

Max Activating Token Index: 401

Text #15

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.5073. Min Act: -0.0000

Data Index: 839095 (The Pile)

Max Activating Token Index: 484

Text #16

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.5740. Min Act: -0.0000

Data Index: 1012732 (The Pile)

Max Activating Token Index: 415

Text #17

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.4852. Min Act: -0.0000

Data Index: 1226182 (The Pile)

Max Activating Token Index: 386

Text #18

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.4698. Min Act: -0.0000

Data Index: 1289576 (The Pile)

Max Activating Token Index: 233

Text #19

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.4683. Min Act: -0.0000

Data Index: 289606 (The Pile)

Max Activating Token Index: 789