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

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

Neuron 3777 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3379. Min Range: -1.3379

Max Act: 1.3379. Min Act: -0.0001

Data Index: 418640 (C4 (Web Text))

Max Activating Token Index: 355

Text #1

Max Range: 1.3379. Min Range: -1.3379

Max Act: 1.0835. Min Act: -0.0001

Data Index: 815875 (C4 (Web Text))

Max Activating Token Index: 866

Text #2

Max Range: 1.3379. Min Range: -1.3379

Max Act: 1.1269. Min Act: -0.0001

Data Index: 183863 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 1.3379. Min Range: -1.3379

Max Act: 1.0126. Min Act: -0.0001

Data Index: 598590 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 1.3379. Min Range: -1.3379

Max Act: 1.0872. Min Act: -0.0001

Data Index: 907533 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 1.3379. Min Range: -1.3379

Max Act: 1.0531. Min Act: -0.0001

Data Index: 428934 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 1.3379. Min Range: -1.3379

Max Act: 1.0482. Min Act: -0.0001

Data Index: 441925 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 1.3379. Min Range: -1.3379

Max Act: 1.1679. Min Act: -0.0001

Data Index: 1096602 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 1.3379. Min Range: -1.3379

Max Act: 1.1705. Min Act: -0.0001

Data Index: 124716 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 1.3379. Min Range: -1.3379

Max Act: 1.1269. Min Act: -0.0001

Data Index: 1123263 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 1.3379. Min Range: -1.3379

Max Act: 1.1122. Min Act: -0.0001

Data Index: 838689 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 1.3379. Min Range: -1.3379

Max Act: 1.0346. Min Act: -0.0001

Data Index: 317662 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 1.3379. Min Range: -1.3379

Max Act: 1.0577. Min Act: -0.0001

Data Index: 586202 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 1.3379. Min Range: -1.3379

Max Act: 0.8911. Min Act: -0.0001

Data Index: 1348551 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 1.3379. Min Range: -1.3379

Max Act: 0.9331. Min Act: -0.0001

Data Index: 58668 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 1.3379. Min Range: -1.3379

Max Act: 1.0789. Min Act: -0.0001

Data Index: 278810 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 1.3379. Min Range: -1.3379

Max Act: 0.8796. Min Act: -0.0001

Data Index: 1161833 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 1.3379. Min Range: -1.3379

Max Act: 0.9498. Min Act: -0.0001

Data Index: 567493 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 1.3379. Min Range: -1.3379

Max Act: 1.0065. Min Act: -0.0001

Data Index: 255736 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 1.3379. Min Range: -1.3379

Max Act: 1.0341. Min Act: -0.0001

Data Index: 258020 (C4 (Web Text))

Max Activating Token Index: 515