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

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

Neuron 3256 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0447. Min Act: -0.0002

Data Index: 934483 (C4 (Web Text))

Max Activating Token Index: 805

Text #1

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0478. Min Act: -0.0002

Data Index: 184077 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0460. Min Act: -0.0002

Data Index: 171119 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0371. Min Act: -0.0002

Data Index: 1149607 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0382. Min Act: -0.0002

Data Index: 337759 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0438. Min Act: -0.0002

Data Index: 569966 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0314. Min Act: -0.0002

Data Index: 107031 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0377. Min Act: -0.0002

Data Index: 1255411 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0401. Min Act: -0.0002

Data Index: 1173118 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0394. Min Act: -0.0002

Data Index: 884000 (C4 (Web Text))

Max Activating Token Index: 632

Text #10

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0405. Min Act: -0.0002

Data Index: 562876 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0381. Min Act: -0.0002

Data Index: 27814 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0401. Min Act: -0.0002

Data Index: 818298 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0351. Min Act: -0.0002

Data Index: 1314208 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0349. Min Act: -0.0002

Data Index: 621570 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0328. Min Act: -0.0002

Data Index: 385947 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0383. Min Act: -0.0002

Data Index: 1134204 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0356. Min Act: -0.0002

Data Index: 681808 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0395. Min Act: -0.0002

Data Index: 70141 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0400. Min Act: -0.0002

Data Index: 1036347 (C4 (Web Text))

Max Activating Token Index: 146