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

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

Neuron 1596 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: 1.6521. Min Range: -1.6521

Max Act: 1.6521. Min Act: -0.0000

Data Index: 341822 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.4416. Min Act: -0.0000

Data Index: 207200 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.2990. Min Act: -0.0000

Data Index: 908839 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.0440. Min Act: -0.0000

Data Index: 1088913 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.3102. Min Act: -0.0000

Data Index: 79478 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.3664. Min Act: -0.0000

Data Index: 903764 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.3542. Min Act: -0.0000

Data Index: 241905 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.3310. Min Act: -0.0000

Data Index: 119072 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.2947. Min Act: -0.0000

Data Index: 84949 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.1834. Min Act: -0.0000

Data Index: 475291 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.2755. Min Act: -0.0000

Data Index: 96345 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.3052. Min Act: -0.0000

Data Index: 1345428 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.2999. Min Act: -0.0000

Data Index: 86220 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.2016. Min Act: -0.0000

Data Index: 641429 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.2367. Min Act: -0.0000

Data Index: 908625 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.1961. Min Act: -0.0000

Data Index: 796569 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.1266. Min Act: -0.0000

Data Index: 844671 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.1824. Min Act: -0.0000

Data Index: 215079 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.1294. Min Act: -0.0000

Data Index: 868624 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.0850. Min Act: -0.0000

Data Index: 1289129 (C4 (Web Text))

Max Activating Token Index: 1004