Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1389 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 2.4227. Min Range: -2.4227

Max Act: 2.3948. Min Act: -0.0002

Data Index: 678454 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 2.4227. Min Range: -2.4227

Max Act: 2.3920. Min Act: -0.0002

Data Index: 1011190 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 2.4227. Min Range: -2.4227

Max Act: 2.4227. Min Act: -0.0002

Data Index: 733126 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 2.4227. Min Range: -2.4227

Max Act: 2.3576. Min Act: -0.0002

Data Index: 175375 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 2.4227. Min Range: -2.4227

Max Act: 2.3130. Min Act: -0.0002

Data Index: 420236 (C4 (Web Text))

Max Activating Token Index: 120

Text #5

Max Range: 2.4227. Min Range: -2.4227

Max Act: 2.3053. Min Act: -0.0002

Data Index: 100855 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 2.4227. Min Range: -2.4227

Max Act: 2.2741. Min Act: -0.0002

Data Index: 730077 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 2.4227. Min Range: -2.4227

Max Act: 2.2459. Min Act: -0.0002

Data Index: 1085173 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 2.4227. Min Range: -2.4227

Max Act: 2.2231. Min Act: -0.0002

Data Index: 155457 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 2.4227. Min Range: -2.4227

Max Act: 2.1865. Min Act: -0.0002

Data Index: 959744 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 2.4227. Min Range: -2.4227

Max Act: 2.2995. Min Act: -0.0002

Data Index: 254319 (C4 (Web Text))

Max Activating Token Index: 279

Text #11

Max Range: 2.4227. Min Range: -2.4227

Max Act: 2.2671. Min Act: -0.0002

Data Index: 420279 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 2.4227. Min Range: -2.4227

Max Act: 2.2758. Min Act: -0.0002

Data Index: 89879 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 2.4227. Min Range: -2.4227

Max Act: 2.1659. Min Act: -0.0002

Data Index: 1322197 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 2.4227. Min Range: -2.4227

Max Act: 2.2384. Min Act: -0.0002

Data Index: 73767 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 2.4227. Min Range: -2.4227

Max Act: 2.1691. Min Act: -0.0002

Data Index: 845917 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 2.4227. Min Range: -2.4227

Max Act: 2.1985. Min Act: -0.0002

Data Index: 871382 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 2.4227. Min Range: -2.4227

Max Act: 2.1391. Min Act: -0.0002

Data Index: 73419 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 2.4227. Min Range: -2.4227

Max Act: 2.2077. Min Act: -0.0002

Data Index: 828925 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 2.4227. Min Range: -2.4227

Max Act: 2.2003. Min Act: -0.0002

Data Index: 119110 (C4 (Web Text))

Max Activating Token Index: 558