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

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

Neuron 3610 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8521. Min Range: -2.8521

Max Act: 2.8521. Min Act: -0.0000

Data Index: 1120196 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 2.8521. Min Range: -2.8521

Max Act: 1.9017. Min Act: -0.0000

Data Index: 136578 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 2.8521. Min Range: -2.8521

Max Act: 1.8525. Min Act: -0.0000

Data Index: 911698 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 2.8521. Min Range: -2.8521

Max Act: 1.8220. Min Act: -0.0000

Data Index: 48144 (C4 (Web Text))

Max Activating Token Index: 450

Text #4

Max Range: 2.8521. Min Range: -2.8521

Max Act: 1.8034. Min Act: -0.0000

Data Index: 230945 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 2.8521. Min Range: -2.8521

Max Act: 1.6884. Min Act: -0.0000

Data Index: 206163 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 2.8521. Min Range: -2.8521

Max Act: 1.7837. Min Act: -0.0000

Data Index: 129160 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 2.8521. Min Range: -2.8521

Max Act: 1.6946. Min Act: -0.0000

Data Index: 161284 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 2.8521. Min Range: -2.8521

Max Act: 1.6426. Min Act: -0.0000

Data Index: 851664 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 2.8521. Min Range: -2.8521

Max Act: 1.6953. Min Act: -0.0000

Data Index: 813007 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 2.8521. Min Range: -2.8521

Max Act: 1.2153. Min Act: -0.0000

Data Index: 1326855 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 2.8521. Min Range: -2.8521

Max Act: 1.0839. Min Act: -0.0000

Data Index: 230989 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 2.8521. Min Range: -2.8521

Max Act: 1.1308. Min Act: -0.0000

Data Index: 621578 (C4 (Web Text))

Max Activating Token Index: 798

Text #13

Max Range: 2.8521. Min Range: -2.8521

Max Act: 1.0804. Min Act: -0.0000

Data Index: 643756 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 2.8521. Min Range: -2.8521

Max Act: 1.0674. Min Act: -0.0000

Data Index: 1288576 (C4 (Web Text))

Max Activating Token Index: 206

Text #15

Max Range: 2.8521. Min Range: -2.8521

Max Act: 1.1429. Min Act: -0.0000

Data Index: 1112531 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 2.8521. Min Range: -2.8521

Max Act: 1.0369. Min Act: -0.0000

Data Index: 265454 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 2.8521. Min Range: -2.8521

Max Act: 1.1168. Min Act: -0.0000

Data Index: 871870 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 2.8521. Min Range: -2.8521

Max Act: 0.9106. Min Act: -0.0000

Data Index: 749334 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 2.8521. Min Range: -2.8521

Max Act: 0.9644. Min Act: -0.0000

Data Index: 1325459 (C4 (Web Text))

Max Activating Token Index: 272