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

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

Neuron 4796 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: 1.2724. Min Range: -1.2724

Max Act: 1.2724. Min Act: -0.0002

Data Index: 34812 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 1.2724. Min Range: -1.2724

Max Act: 1.2622. Min Act: -0.0002

Data Index: 534746 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 1.2724. Min Range: -1.2724

Max Act: 1.1705. Min Act: -0.0002

Data Index: 990724 (C4 (Web Text))

Max Activating Token Index: 625

Text #3

Max Range: 1.2724. Min Range: -1.2724

Max Act: 1.1428. Min Act: -0.0002

Data Index: 257548 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 1.2724. Min Range: -1.2724

Max Act: 1.1259. Min Act: -0.0002

Data Index: 563924 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 1.2724. Min Range: -1.2724

Max Act: 1.1007. Min Act: -0.0002

Data Index: 1310494 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 1.2724. Min Range: -1.2724

Max Act: 1.0985. Min Act: -0.0002

Data Index: 431928 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 1.2724. Min Range: -1.2724

Max Act: 1.0680. Min Act: -0.0002

Data Index: 252535 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 1.2724. Min Range: -1.2724

Max Act: 1.0601. Min Act: -0.0002

Data Index: 855074 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 1.2724. Min Range: -1.2724

Max Act: 1.0623. Min Act: -0.0002

Data Index: 335284 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 1.2724. Min Range: -1.2724

Max Act: 1.0267. Min Act: -0.0002

Data Index: 711646 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 1.2724. Min Range: -1.2724

Max Act: 1.0246. Min Act: -0.0002

Data Index: 899906 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.9953. Min Act: -0.0002

Data Index: 722913 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 1.2724. Min Range: -1.2724

Max Act: 1.0013. Min Act: -0.0002

Data Index: 354271 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.9815. Min Act: -0.0002

Data Index: 45351 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.9720. Min Act: -0.0002

Data Index: 746801 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.9597. Min Act: -0.0002

Data Index: 859740 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.9696. Min Act: -0.0002

Data Index: 1202838 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.9751. Min Act: -0.0002

Data Index: 823765 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.9533. Min Act: -0.0002

Data Index: 642808 (C4 (Web Text))

Max Activating Token Index: 806