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

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

Neuron 6071 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: 1.4193. Min Range: -1.4193

Max Act: 1.4193. Min Act: -0.0002

Data Index: 54434 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 1.4193. Min Range: -1.4193

Max Act: 1.3608. Min Act: -0.0002

Data Index: 166972 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 1.4193. Min Range: -1.4193

Max Act: 1.3288. Min Act: -0.0002

Data Index: 688461 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 1.4193. Min Range: -1.4193

Max Act: 1.3012. Min Act: -0.0002

Data Index: 1160382 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 1.4193. Min Range: -1.4193

Max Act: 1.3019. Min Act: -0.0002

Data Index: 123337 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 1.4193. Min Range: -1.4193

Max Act: 1.2555. Min Act: -0.0002

Data Index: 81554 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 1.4193. Min Range: -1.4193

Max Act: 1.2438. Min Act: -0.0002

Data Index: 1076962 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 1.4193. Min Range: -1.4193

Max Act: 1.2666. Min Act: -0.0002

Data Index: 920245 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 1.4193. Min Range: -1.4193

Max Act: 1.2205. Min Act: -0.0002

Data Index: 594731 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 1.4193. Min Range: -1.4193

Max Act: 1.2209. Min Act: -0.0002

Data Index: 123056 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 1.4193. Min Range: -1.4193

Max Act: 1.2123. Min Act: -0.0002

Data Index: 818159 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 1.4193. Min Range: -1.4193

Max Act: 1.2223. Min Act: -0.0002

Data Index: 735470 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 1.4193. Min Range: -1.4193

Max Act: 1.2112. Min Act: -0.0002

Data Index: 955667 (C4 (Web Text))

Max Activating Token Index: 324

Text #13

Max Range: 1.4193. Min Range: -1.4193

Max Act: 1.1724. Min Act: -0.0002

Data Index: 1016012 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 1.4193. Min Range: -1.4193

Max Act: 1.2037. Min Act: -0.0002

Data Index: 1196715 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 1.4193. Min Range: -1.4193

Max Act: 1.2077. Min Act: -0.0002

Data Index: 1131199 (C4 (Web Text))

Max Activating Token Index: 628

Text #16

Max Range: 1.4193. Min Range: -1.4193

Max Act: 1.1814. Min Act: -0.0002

Data Index: 1097403 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 1.4193. Min Range: -1.4193

Max Act: 1.1638. Min Act: -0.0002

Data Index: 1286909 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 1.4193. Min Range: -1.4193

Max Act: 1.1744. Min Act: -0.0002

Data Index: 888570 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 1.4193. Min Range: -1.4193

Max Act: 1.1934. Min Act: -0.0002

Data Index: 128700 (C4 (Web Text))

Max Activating Token Index: 9