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

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

Neuron 3934 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: 1.2697. Min Range: -1.2697

Max Act: 1.2697. Min Act: -0.0000

Data Index: 1286906 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 1.2697. Min Range: -1.2697

Max Act: 1.2201. Min Act: -0.0000

Data Index: 811913 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 1.2697. Min Range: -1.2697

Max Act: 1.1274. Min Act: -0.0000

Data Index: 111583 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 1.2697. Min Range: -1.2697

Max Act: 1.1698. Min Act: -0.0000

Data Index: 896448 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 1.2697. Min Range: -1.2697

Max Act: 1.0697. Min Act: -0.0000

Data Index: 4819 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 1.2697. Min Range: -1.2697

Max Act: 1.0818. Min Act: -0.0000

Data Index: 580693 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 1.2697. Min Range: -1.2697

Max Act: 0.9881. Min Act: -0.0000

Data Index: 1330818 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 1.2697. Min Range: -1.2697

Max Act: 1.0739. Min Act: -0.0000

Data Index: 1100007 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 1.2697. Min Range: -1.2697

Max Act: 1.0293. Min Act: -0.0000

Data Index: 242472 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 1.2697. Min Range: -1.2697

Max Act: 1.0289. Min Act: -0.0000

Data Index: 899960 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 1.2697. Min Range: -1.2697

Max Act: 1.0628. Min Act: -0.0000

Data Index: 636445 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 1.2697. Min Range: -1.2697

Max Act: 0.9912. Min Act: -0.0000

Data Index: 1034552 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 1.2697. Min Range: -1.2697

Max Act: 1.1338. Min Act: -0.0000

Data Index: 816503 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 1.2697. Min Range: -1.2697

Max Act: 1.0392. Min Act: -0.0000

Data Index: 400529 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 1.2697. Min Range: -1.2697

Max Act: 1.0169. Min Act: -0.0000

Data Index: 1199108 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 1.2697. Min Range: -1.2697

Max Act: 0.9209. Min Act: -0.0000

Data Index: 978714 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 1.2697. Min Range: -1.2697

Max Act: 0.9388. Min Act: -0.0000

Data Index: 248312 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 1.2697. Min Range: -1.2697

Max Act: 0.9693. Min Act: -0.0000

Data Index: 987180 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 1.2697. Min Range: -1.2697

Max Act: 0.9837. Min Act: -0.0000

Data Index: 508142 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 1.2697. Min Range: -1.2697

Max Act: 0.9613. Min Act: -0.0000

Data Index: 834944 (C4 (Web Text))

Max Activating Token Index: 981