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

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

Neuron 2745 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3789. Min Range: -1.3789

Max Act: 1.3735. Min Act: -0.0000

Data Index: 431596 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 1.3789. Min Range: -1.3789

Max Act: 1.3789. Min Act: -0.0000

Data Index: 328028 (C4 (Web Text))

Max Activating Token Index: 815

Text #2

Max Range: 1.3789. Min Range: -1.3789

Max Act: 1.3079. Min Act: -0.0000

Data Index: 317162 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 1.3789. Min Range: -1.3789

Max Act: 1.3075. Min Act: -0.0000

Data Index: 49531 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 1.3789. Min Range: -1.3789

Max Act: 1.2381. Min Act: -0.0000

Data Index: 57513 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 1.3789. Min Range: -1.3789

Max Act: 1.2428. Min Act: -0.0000

Data Index: 479391 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 1.3789. Min Range: -1.3789

Max Act: 1.1892. Min Act: -0.0000

Data Index: 571615 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 1.3789. Min Range: -1.3789

Max Act: 1.1868. Min Act: -0.0000

Data Index: 540125 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 1.3789. Min Range: -1.3789

Max Act: 1.1814. Min Act: -0.0000

Data Index: 225035 (C4 (Web Text))

Max Activating Token Index: 523

Text #9

Max Range: 1.3789. Min Range: -1.3789

Max Act: 1.1433. Min Act: -0.0000

Data Index: 952903 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 1.3789. Min Range: -1.3789

Max Act: 1.2098. Min Act: -0.0000

Data Index: 89770 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 1.3789. Min Range: -1.3789

Max Act: 1.1363. Min Act: -0.0000

Data Index: 324726 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 1.3789. Min Range: -1.3789

Max Act: 1.1529. Min Act: -0.0000

Data Index: 858548 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 1.3789. Min Range: -1.3789

Max Act: 1.1639. Min Act: -0.0000

Data Index: 1164470 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 1.3789. Min Range: -1.3789

Max Act: 1.1321. Min Act: -0.0000

Data Index: 872661 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 1.3789. Min Range: -1.3789

Max Act: 1.1301. Min Act: -0.0000

Data Index: 1063628 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 1.3789. Min Range: -1.3789

Max Act: 1.0870. Min Act: -0.0000

Data Index: 1155507 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 1.3789. Min Range: -1.3789

Max Act: 1.1104. Min Act: -0.0000

Data Index: 1175484 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 1.3789. Min Range: -1.3789

Max Act: 1.0664. Min Act: -0.0000

Data Index: 1158944 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 1.3789. Min Range: -1.3789

Max Act: 1.0836. Min Act: -0.0000

Data Index: 544906 (C4 (Web Text))

Max Activating Token Index: 813