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

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

Neuron 117 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: 1.2905. Min Range: -1.2905

Max Act: 1.2905. Min Act: -0.0000

Data Index: 204789 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 1.2905. Min Range: -1.2905

Max Act: 1.2030. Min Act: -0.0000

Data Index: 1170020 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 1.2905. Min Range: -1.2905

Max Act: 1.1318. Min Act: -0.0000

Data Index: 1244130 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 1.2905. Min Range: -1.2905

Max Act: 1.1376. Min Act: -0.0000

Data Index: 1029596 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 1.2905. Min Range: -1.2905

Max Act: 1.1346. Min Act: -0.0000

Data Index: 806692 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 1.2905. Min Range: -1.2905

Max Act: 1.1813. Min Act: -0.0000

Data Index: 215629 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 1.2905. Min Range: -1.2905

Max Act: 1.0380. Min Act: -0.0000

Data Index: 1015891 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 1.2905. Min Range: -1.2905

Max Act: 1.0610. Min Act: -0.0000

Data Index: 501753 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 1.2905. Min Range: -1.2905

Max Act: 0.9710. Min Act: -0.0000

Data Index: 1356584 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 1.2905. Min Range: -1.2905

Max Act: 1.0205. Min Act: -0.0000

Data Index: 716452 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 1.2905. Min Range: -1.2905

Max Act: 0.9785. Min Act: -0.0000

Data Index: 962906 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 1.2905. Min Range: -1.2905

Max Act: 1.0349. Min Act: -0.0000

Data Index: 196105 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 1.2905. Min Range: -1.2905

Max Act: 0.9101. Min Act: -0.0000

Data Index: 263900 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 1.2905. Min Range: -1.2905

Max Act: 0.9997. Min Act: -0.0000

Data Index: 1262252 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 1.2905. Min Range: -1.2905

Max Act: 0.9451. Min Act: -0.0000

Data Index: 280167 (C4 (Web Text))

Max Activating Token Index: 636

Text #15

Max Range: 1.2905. Min Range: -1.2905

Max Act: 0.9299. Min Act: -0.0000

Data Index: 821223 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 1.2905. Min Range: -1.2905

Max Act: 0.9273. Min Act: -0.0000

Data Index: 927157 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 1.2905. Min Range: -1.2905

Max Act: 0.8508. Min Act: -0.0000

Data Index: 211722 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 1.2905. Min Range: -1.2905

Max Act: 0.9565. Min Act: -0.0000

Data Index: 980824 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 1.2905. Min Range: -1.2905

Max Act: 0.8994. Min Act: -0.0000

Data Index: 26728 (C4 (Web Text))

Max Activating Token Index: 583