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

Dataset: The Pile

Neuron 3634 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: 0.6686. Min Range: -0.6686

Max Act: 0.6686. Min Act: -0.0000

Data Index: 1252859 (The Pile)

Max Activating Token Index: 451

Text #1

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.5354. Min Act: -0.0000

Data Index: 1108423 (The Pile)

Max Activating Token Index: 564

Text #2

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.5351. Min Act: -0.0000

Data Index: 236292 (The Pile)

Max Activating Token Index: 287

Text #3

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.4912. Min Act: -0.0000

Data Index: 1875779 (The Pile)

Max Activating Token Index: 826

Text #4

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.4890. Min Act: -0.0000

Data Index: 110218 (The Pile)

Max Activating Token Index: 363

Text #5

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.4667. Min Act: -0.0000

Data Index: 957725 (The Pile)

Max Activating Token Index: 184

Text #6

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.4609. Min Act: -0.0000

Data Index: 50006 (The Pile)

Max Activating Token Index: 157

Text #7

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.4830. Min Act: -0.0000

Data Index: 301222 (The Pile)

Max Activating Token Index: 138

Text #8

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.4508. Min Act: -0.0000

Data Index: 645878 (The Pile)

Max Activating Token Index: 289

Text #9

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.4254. Min Act: -0.0000

Data Index: 1011505 (The Pile)

Max Activating Token Index: 748

Text #10

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.4570. Min Act: -0.0000

Data Index: 421313 (The Pile)

Max Activating Token Index: 597

Text #11

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.4431. Min Act: -0.0000

Data Index: 1991256 (The Pile)

Max Activating Token Index: 980

Text #12

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.4368. Min Act: -0.0000

Data Index: 1873652 (The Pile)

Max Activating Token Index: 823

Text #13

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.4490. Min Act: -0.0000

Data Index: 94239 (The Pile)

Max Activating Token Index: 218

Text #14

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.4270. Min Act: -0.0000

Data Index: 818273 (The Pile)

Max Activating Token Index: 762

Text #15

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.4316. Min Act: -0.0000

Data Index: 1929412 (The Pile)

Max Activating Token Index: 652

Text #16

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.3939. Min Act: -0.0000

Data Index: 720864 (The Pile)

Max Activating Token Index: 198

Text #17

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.4180. Min Act: -0.0000

Data Index: 1767802 (The Pile)

Max Activating Token Index: 628

Text #18

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.4054. Min Act: -0.0000

Data Index: 1489153 (The Pile)

Max Activating Token Index: 472

Text #19

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.4007. Min Act: -0.0000

Data Index: 1260975 (The Pile)

Max Activating Token Index: 683