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

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

Neuron 3234 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.5565. Min Act: -0.0000

Data Index: 936388 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.4876. Min Act: -0.0000

Data Index: 861538 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.4835. Min Act: -0.0000

Data Index: 792348 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.4417. Min Act: -0.0000

Data Index: 490951 (C4 (Web Text))

Max Activating Token Index: 279

Text #4

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.4395. Min Act: -0.0000

Data Index: 476166 (C4 (Web Text))

Max Activating Token Index: 727

Text #5

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.4485. Min Act: -0.0000

Data Index: 1079717 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.3935. Min Act: -0.0000

Data Index: 1582509 (Python Code)

Max Activating Token Index: 989

Text #7

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.4475. Min Act: -0.0000

Data Index: 721014 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.4047. Min Act: -0.0000

Data Index: 535118 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.3957. Min Act: -0.0000

Data Index: 881461 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.4222. Min Act: -0.0000

Data Index: 1348950 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.4297. Min Act: -0.0000

Data Index: 578468 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.3900. Min Act: -0.0000

Data Index: 1302334 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.3781. Min Act: -0.0000

Data Index: 1350918 (C4 (Web Text))

Max Activating Token Index: 344

Text #14

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.3958. Min Act: -0.0000

Data Index: 818456 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.3968. Min Act: -0.0000

Data Index: 692977 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.3613. Min Act: -0.0000

Data Index: 1596295 (Python Code)

Max Activating Token Index: 542

Text #17

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.3402. Min Act: -0.0000

Data Index: 620458 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.3820. Min Act: -0.0000

Data Index: 1553833 (Python Code)

Max Activating Token Index: 32

Text #19

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.3779. Min Act: -0.0000

Data Index: 764702 (C4 (Web Text))

Max Activating Token Index: 127