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

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

Neuron 3957 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.7799. Min Range: -3.7799

Max Act: 3.7799. Min Act: -0.0000

Data Index: 177586 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 3.7799. Min Range: -3.7799

Max Act: 3.3254. Min Act: -0.0000

Data Index: 699591 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 3.7799. Min Range: -3.7799

Max Act: 3.3153. Min Act: -0.0000

Data Index: 894235 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 3.7799. Min Range: -3.7799

Max Act: 3.1867. Min Act: -0.0000

Data Index: 135254 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 3.7799. Min Range: -3.7799

Max Act: 3.0153. Min Act: -0.0000

Data Index: 57004 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 3.7799. Min Range: -3.7799

Max Act: 3.1821. Min Act: -0.0000

Data Index: 576683 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 3.7799. Min Range: -3.7799

Max Act: 3.0180. Min Act: -0.0000

Data Index: 494145 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 3.7799. Min Range: -3.7799

Max Act: 2.4351. Min Act: -0.0000

Data Index: 191138 (C4 (Web Text))

Max Activating Token Index: 790

Text #8

Max Range: 3.7799. Min Range: -3.7799

Max Act: 2.7706. Min Act: -0.0000

Data Index: 734594 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 3.7799. Min Range: -3.7799

Max Act: 3.0043. Min Act: -0.0000

Data Index: 1213393 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 3.7799. Min Range: -3.7799

Max Act: 2.8528. Min Act: -0.0000

Data Index: 28350 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 3.7799. Min Range: -3.7799

Max Act: 2.9773. Min Act: -0.0000

Data Index: 982127 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 3.7799. Min Range: -3.7799

Max Act: 2.5234. Min Act: -0.0000

Data Index: 1240855 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 3.7799. Min Range: -3.7799

Max Act: 2.7310. Min Act: -0.0000

Data Index: 413118 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 3.7799. Min Range: -3.7799

Max Act: 2.8725. Min Act: -0.0000

Data Index: 860887 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 3.7799. Min Range: -3.7799

Max Act: 2.8016. Min Act: -0.0000

Data Index: 270310 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 3.7799. Min Range: -3.7799

Max Act: 2.6211. Min Act: -0.0000

Data Index: 417350 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 3.7799. Min Range: -3.7799

Max Act: 2.4175. Min Act: -0.0000

Data Index: 79904 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 3.7799. Min Range: -3.7799

Max Act: 2.3223. Min Act: -0.0000

Data Index: 238875 (C4 (Web Text))

Max Activating Token Index: 133

Text #19

Max Range: 3.7799. Min Range: -3.7799

Max Act: 2.6339. Min Act: -0.0000

Data Index: 495552 (C4 (Web Text))

Max Activating Token Index: 76