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

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

Neuron 4689 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2784. Min Act: -0.0000

Data Index: 908429 (C4 (Web Text))

Max Activating Token Index: 742

Text #1

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2743. Min Act: -0.0000

Data Index: 1059424 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.3071. Min Act: -0.0000

Data Index: 1035153 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2933. Min Act: -0.0000

Data Index: 102075 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2704. Min Act: -0.0000

Data Index: 1028778 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2540. Min Act: -0.0000

Data Index: 482639 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2929. Min Act: -0.0000

Data Index: 1024700 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2705. Min Act: -0.0000

Data Index: 304584 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2552. Min Act: -0.0000

Data Index: 739171 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2642. Min Act: -0.0000

Data Index: 690846 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2599. Min Act: -0.0000

Data Index: 827794 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2643. Min Act: -0.0000

Data Index: 213635 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2289. Min Act: -0.0000

Data Index: 946184 (C4 (Web Text))

Max Activating Token Index: 170

Text #13

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2382. Min Act: -0.0000

Data Index: 324423 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2222. Min Act: -0.0000

Data Index: 530137 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2237. Min Act: -0.0000

Data Index: 968961 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2449. Min Act: -0.0000

Data Index: 750670 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2357. Min Act: -0.0000

Data Index: 184053 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2110. Min Act: -0.0000

Data Index: 643748 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2015. Min Act: -0.0000

Data Index: 828627 (C4 (Web Text))

Max Activating Token Index: 483