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

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

Neuron 3520 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0666. Min Range: -4.0666

Max Act: 3.9859. Min Act: -0.0001

Data Index: 295904 (C4 (Web Text))

Max Activating Token Index: 493

Text #1

Max Range: 4.0666. Min Range: -4.0666

Max Act: 3.9024. Min Act: -0.0001

Data Index: 92845 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 4.0666. Min Range: -4.0666

Max Act: 4.0666. Min Act: -0.0001

Data Index: 98375 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 4.0666. Min Range: -4.0666

Max Act: 3.7597. Min Act: -0.0001

Data Index: 1151330 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 4.0666. Min Range: -4.0666

Max Act: 3.7515. Min Act: -0.0001

Data Index: 984418 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 4.0666. Min Range: -4.0666

Max Act: 3.4978. Min Act: -0.0000

Data Index: 266283 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 4.0666. Min Range: -4.0666

Max Act: 3.7801. Min Act: -0.0000

Data Index: 1357990 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 4.0666. Min Range: -4.0666

Max Act: 3.7720. Min Act: -0.0001

Data Index: 874050 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 4.0666. Min Range: -4.0666

Max Act: 3.9315. Min Act: -0.0000

Data Index: 129744 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 4.0666. Min Range: -4.0666

Max Act: 4.0605. Min Act: -0.0001

Data Index: 902219 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 4.0666. Min Range: -4.0666

Max Act: 3.5385. Min Act: -0.0001

Data Index: 583031 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 4.0666. Min Range: -4.0666

Max Act: 3.6244. Min Act: -0.0000

Data Index: 30718 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 4.0666. Min Range: -4.0666

Max Act: 3.6343. Min Act: -0.0001

Data Index: 74246 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 4.0666. Min Range: -4.0666

Max Act: 3.4818. Min Act: -0.0000

Data Index: 321862 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 4.0666. Min Range: -4.0666

Max Act: 3.6049. Min Act: -0.0001

Data Index: 38366 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 4.0666. Min Range: -4.0666

Max Act: 3.4309. Min Act: -0.0001

Data Index: 728536 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 4.0666. Min Range: -4.0666

Max Act: 3.7150. Min Act: -0.0001

Data Index: 977581 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 4.0666. Min Range: -4.0666

Max Act: 3.2435. Min Act: -0.0000

Data Index: 774497 (C4 (Web Text))

Max Activating Token Index: 940

Text #18

Max Range: 4.0666. Min Range: -4.0666

Max Act: 3.4983. Min Act: -0.0000

Data Index: 650944 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 4.0666. Min Range: -4.0666

Max Act: 3.2067. Min Act: -0.0001

Data Index: 1341318 (C4 (Web Text))

Max Activating Token Index: 431