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

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

Neuron 2678 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2936. Min Range: -1.2936

Max Act: 1.2936. Min Act: -0.0000

Data Index: 818597 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 1.2936. Min Range: -1.2936

Max Act: 1.1300. Min Act: -0.0000

Data Index: 276596 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 1.2936. Min Range: -1.2936

Max Act: 1.0811. Min Act: -0.0000

Data Index: 1046166 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 1.2936. Min Range: -1.2936

Max Act: 1.0479. Min Act: -0.0000

Data Index: 730500 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.9087. Min Act: -0.0000

Data Index: 796849 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.8783. Min Act: -0.0000

Data Index: 885583 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.7878. Min Act: -0.0000

Data Index: 905786 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.8457. Min Act: -0.0000

Data Index: 116863 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.8232. Min Act: -0.0000

Data Index: 1312168 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.7702. Min Act: -0.0000

Data Index: 1233320 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.7852. Min Act: -0.0000

Data Index: 401857 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.7674. Min Act: -0.0000

Data Index: 1028533 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.7525. Min Act: -0.0000

Data Index: 754556 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.7527. Min Act: -0.0000

Data Index: 805392 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.7690. Min Act: -0.0000

Data Index: 1128532 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.7909. Min Act: -0.0000

Data Index: 274639 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.7307. Min Act: -0.0000

Data Index: 370249 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.7267. Min Act: -0.0000

Data Index: 1067179 (C4 (Web Text))

Max Activating Token Index: 274

Text #18

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.7380. Min Act: -0.0000

Data Index: 463102 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.6866. Min Act: -0.0000

Data Index: 321676 (C4 (Web Text))

Max Activating Token Index: 65