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

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

Neuron 190 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3066. Min Range: -1.3066

Max Act: 1.3066. Min Act: -0.0000

Data Index: 1085 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 1.3066. Min Range: -1.3066

Max Act: 1.0824. Min Act: -0.0001

Data Index: 433732 (C4 (Web Text))

Max Activating Token Index: 765

Text #2

Max Range: 1.3066. Min Range: -1.3066

Max Act: 1.0535. Min Act: -0.0000

Data Index: 553764 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 1.3066. Min Range: -1.3066

Max Act: 1.0489. Min Act: -0.0000

Data Index: 1023734 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 1.3066. Min Range: -1.3066

Max Act: 0.8993. Min Act: -0.0000

Data Index: 235156 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 1.3066. Min Range: -1.3066

Max Act: 1.0544. Min Act: -0.0000

Data Index: 990364 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 1.3066. Min Range: -1.3066

Max Act: 1.1079. Min Act: -0.0000

Data Index: 1022590 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 1.3066. Min Range: -1.3066

Max Act: 1.0017. Min Act: -0.0001

Data Index: 628086 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 1.3066. Min Range: -1.3066

Max Act: 1.0070. Min Act: -0.0001

Data Index: 1211071 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 1.3066. Min Range: -1.3066

Max Act: 1.0629. Min Act: -0.0001

Data Index: 483681 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 1.3066. Min Range: -1.3066

Max Act: 1.0345. Min Act: -0.0000

Data Index: 1090394 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 1.3066. Min Range: -1.3066

Max Act: 0.9243. Min Act: -0.0000

Data Index: 431333 (C4 (Web Text))

Max Activating Token Index: 68

Text #12

Max Range: 1.3066. Min Range: -1.3066

Max Act: 1.0106. Min Act: -0.0000

Data Index: 1353982 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 1.3066. Min Range: -1.3066

Max Act: 1.0961. Min Act: -0.0001

Data Index: 836752 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 1.3066. Min Range: -1.3066

Max Act: 1.0638. Min Act: -0.0000

Data Index: 669050 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 1.3066. Min Range: -1.3066

Max Act: 1.0205. Min Act: -0.0000

Data Index: 1204118 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 1.3066. Min Range: -1.3066

Max Act: 0.9607. Min Act: -0.0000

Data Index: 577695 (C4 (Web Text))

Max Activating Token Index: 992

Text #17

Max Range: 1.3066. Min Range: -1.3066

Max Act: 0.9240. Min Act: -0.0000

Data Index: 1270554 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 1.3066. Min Range: -1.3066

Max Act: 0.9465. Min Act: -0.0001

Data Index: 172689 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 1.3066. Min Range: -1.3066

Max Act: 1.0329. Min Act: -0.0000

Data Index: 1239439 (C4 (Web Text))

Max Activating Token Index: 961