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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1657 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8244. Min Range: -0.8244

Max Act: 0.8162. Min Act: -0.0001

Data Index: 685407 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 0.8244. Min Range: -0.8244

Max Act: 0.8063. Min Act: -0.0001

Data Index: 1194477 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 0.8244. Min Range: -0.8244

Max Act: 0.8244. Min Act: -0.0001

Data Index: 880482 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 0.8244. Min Range: -0.8244

Max Act: 0.7063. Min Act: -0.0002

Data Index: 426025 (C4 (Web Text))

Max Activating Token Index: 754

Text #4

Max Range: 0.8244. Min Range: -0.8244

Max Act: 0.7919. Min Act: -0.0001

Data Index: 524631 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 0.8244. Min Range: -0.8244

Max Act: 0.7428. Min Act: -0.0001

Data Index: 850386 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 0.8244. Min Range: -0.8244

Max Act: 0.6350. Min Act: -0.0001

Data Index: 960285 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 0.8244. Min Range: -0.8244

Max Act: 0.7467. Min Act: -0.0002

Data Index: 930332 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 0.8244. Min Range: -0.8244

Max Act: 0.7142. Min Act: -0.0001

Data Index: 1237985 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 0.8244. Min Range: -0.8244

Max Act: 0.6816. Min Act: -0.0002

Data Index: 185256 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 0.8244. Min Range: -0.8244

Max Act: 0.6548. Min Act: -0.0002

Data Index: 814297 (C4 (Web Text))

Max Activating Token Index: 706

Text #11

Max Range: 0.8244. Min Range: -0.8244

Max Act: 0.6580. Min Act: -0.0002

Data Index: 240655 (C4 (Web Text))

Max Activating Token Index: 573

Text #12

Max Range: 0.8244. Min Range: -0.8244

Max Act: 0.6433. Min Act: -0.0001

Data Index: 1029137 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 0.8244. Min Range: -0.8244

Max Act: 0.6216. Min Act: -0.0002

Data Index: 1043423 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 0.8244. Min Range: -0.8244

Max Act: 0.6318. Min Act: -0.0002

Data Index: 79890 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 0.8244. Min Range: -0.8244

Max Act: 0.6311. Min Act: -0.0001

Data Index: 1234026 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 0.8244. Min Range: -0.8244

Max Act: 0.5822. Min Act: -0.0002

Data Index: 1356304 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 0.8244. Min Range: -0.8244

Max Act: 0.6049. Min Act: -0.0001

Data Index: 163712 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 0.8244. Min Range: -0.8244

Max Act: 0.5655. Min Act: -0.0001

Data Index: 337600 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 0.8244. Min Range: -0.8244

Max Act: 0.5718. Min Act: -0.0002

Data Index: 606215 (C4 (Web Text))

Max Activating Token Index: 864