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

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

Neuron 3114 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2537. Min Range: -1.2537

Max Act: 1.2537. Min Act: -0.0003

Data Index: 165248 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 1.2537. Min Range: -1.2537

Max Act: 1.2299. Min Act: -0.0003

Data Index: 842955 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 1.2537. Min Range: -1.2537

Max Act: 1.0849. Min Act: -0.0003

Data Index: 600322 (C4 (Web Text))

Max Activating Token Index: 851

Text #3

Max Range: 1.2537. Min Range: -1.2537

Max Act: 1.1854. Min Act: -0.0002

Data Index: 768662 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 1.2537. Min Range: -1.2537

Max Act: 1.1485. Min Act: -0.0003

Data Index: 253508 (C4 (Web Text))

Max Activating Token Index: 485

Text #5

Max Range: 1.2537. Min Range: -1.2537

Max Act: 1.1152. Min Act: -0.0002

Data Index: 1315829 (C4 (Web Text))

Max Activating Token Index: 534

Text #6

Max Range: 1.2537. Min Range: -1.2537

Max Act: 1.1415. Min Act: -0.0003

Data Index: 935887 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 1.2537. Min Range: -1.2537

Max Act: 1.1052. Min Act: -0.0003

Data Index: 584696 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 1.2537. Min Range: -1.2537

Max Act: 1.1318. Min Act: -0.0003

Data Index: 685072 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 1.2537. Min Range: -1.2537

Max Act: 1.0860. Min Act: -0.0002

Data Index: 666266 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 1.2537. Min Range: -1.2537

Max Act: 1.0842. Min Act: -0.0003

Data Index: 886732 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 1.2537. Min Range: -1.2537

Max Act: 1.1093. Min Act: -0.0003

Data Index: 893303 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 1.2537. Min Range: -1.2537

Max Act: 1.0993. Min Act: -0.0003

Data Index: 1047633 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 1.2537. Min Range: -1.2537

Max Act: 1.0965. Min Act: -0.0002

Data Index: 589159 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 1.2537. Min Range: -1.2537

Max Act: 1.0237. Min Act: -0.0003

Data Index: 976867 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 1.2537. Min Range: -1.2537

Max Act: 1.1571. Min Act: -0.0003

Data Index: 1072071 (C4 (Web Text))

Max Activating Token Index: 217

Text #16

Max Range: 1.2537. Min Range: -1.2537

Max Act: 1.0231. Min Act: -0.0003

Data Index: 1180485 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 1.2537. Min Range: -1.2537

Max Act: 0.9905. Min Act: -0.0002

Data Index: 445947 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 1.2537. Min Range: -1.2537

Max Act: 0.9557. Min Act: -0.0003

Data Index: 1285740 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 1.2537. Min Range: -1.2537

Max Act: 0.9473. Min Act: -0.0002

Data Index: 1348930 (C4 (Web Text))

Max Activating Token Index: 248