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

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

Neuron 4008 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: 0.0688. Min Range: -0.0688

Max Act: 0.0688. Min Act: -0.0002

Data Index: 264348 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0675. Min Act: -0.0003

Data Index: 1268346 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0560. Min Act: -0.0003

Data Index: 1141531 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0567. Min Act: -0.0003

Data Index: 1203798 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0535. Min Act: -0.0003

Data Index: 1079960 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0528. Min Act: -0.0002

Data Index: 1224805 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0497. Min Act: -0.0003

Data Index: 647849 (C4 (Web Text))

Max Activating Token Index: 464

Text #7

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0485. Min Act: -0.0002

Data Index: 818997 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0502. Min Act: -0.0002

Data Index: 70293 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0519. Min Act: -0.0003

Data Index: 198604 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0480. Min Act: -0.0003

Data Index: 180657 (C4 (Web Text))

Max Activating Token Index: 346

Text #11

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0482. Min Act: -0.0003

Data Index: 1217037 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0491. Min Act: -0.0002

Data Index: 728130 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0471. Min Act: -0.0003

Data Index: 339234 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0523. Min Act: -0.0003

Data Index: 400443 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0442. Min Act: -0.0003

Data Index: 152490 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0482. Min Act: -0.0003

Data Index: 1081677 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0491. Min Act: -0.0003

Data Index: 215529 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0455. Min Act: -0.0003

Data Index: 282303 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0469. Min Act: -0.0003

Data Index: 174715 (C4 (Web Text))

Max Activating Token Index: 906