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

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

Neuron 3238 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.8959. Min Act: -0.0003

Data Index: 417336 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.8302. Min Act: -0.0002

Data Index: 136222 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.7264. Min Act: -0.0003

Data Index: 232068 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.6948. Min Act: -0.0003

Data Index: 761386 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.7102. Min Act: -0.0003

Data Index: 405638 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.7014. Min Act: -0.0003

Data Index: 534788 (C4 (Web Text))

Max Activating Token Index: 464

Text #6

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.6928. Min Act: -0.0003

Data Index: 120800 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.6922. Min Act: -0.0003

Data Index: 566194 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.6884. Min Act: -0.0003

Data Index: 330524 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.6872. Min Act: -0.0003

Data Index: 1256096 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.6865. Min Act: -0.0002

Data Index: 712568 (C4 (Web Text))

Max Activating Token Index: 385

Text #11

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.6862. Min Act: -0.0002

Data Index: 1291584 (C4 (Web Text))

Max Activating Token Index: 709

Text #12

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.7063. Min Act: -0.0003

Data Index: 1075859 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.6790. Min Act: -0.0003

Data Index: 136147 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.6769. Min Act: -0.0003

Data Index: 1085345 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.6715. Min Act: -0.0003

Data Index: 94469 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.6708. Min Act: -0.0003

Data Index: 634251 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.6509. Min Act: -0.0003

Data Index: 592581 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.6711. Min Act: -0.0003

Data Index: 895784 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.6684. Min Act: -0.0002

Data Index: 73313 (C4 (Web Text))

Max Activating Token Index: 382