Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 15 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0838. Min Act: -0.0002

Data Index: 488847 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0753. Min Act: -0.0002

Data Index: 143828 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0723. Min Act: -0.0002

Data Index: 879759 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0685. Min Act: -0.0002

Data Index: 544725 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0677. Min Act: -0.0002

Data Index: 656743 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0659. Min Act: -0.0002

Data Index: 1171837 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0635. Min Act: -0.0002

Data Index: 1416317 (Python Code)

Max Activating Token Index: 81

Text #7

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0628. Min Act: -0.0002

Data Index: 249109 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0574. Min Act: -0.0002

Data Index: 2760 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0599. Min Act: -0.0002

Data Index: 399671 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0602. Min Act: -0.0002

Data Index: 998554 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0594. Min Act: -0.0002

Data Index: 362051 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0586. Min Act: -0.0002

Data Index: 960047 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0574. Min Act: -0.0002

Data Index: 494985 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0523. Min Act: -0.0002

Data Index: 718535 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1187231 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0522. Min Act: -0.0002

Data Index: 996332 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0539. Min Act: -0.0002

Data Index: 752610 (C4 (Web Text))

Max Activating Token Index: 378

Text #18

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0536. Min Act: -0.0002

Data Index: 396530 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0531. Min Act: -0.0002

Data Index: 1322870 (C4 (Web Text))

Max Activating Token Index: 453