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

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

Neuron 3398 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0170. Min Range: -1.0170

Max Act: 1.0170. Min Act: -0.0000

Data Index: 751993 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.9186. Min Act: -0.0000

Data Index: 615564 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.9019. Min Act: -0.0000

Data Index: 770879 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.8746. Min Act: -0.0000

Data Index: 135592 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.8708. Min Act: -0.0000

Data Index: 823914 (C4 (Web Text))

Max Activating Token Index: 776

Text #5

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.8579. Min Act: -0.0000

Data Index: 414619 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.7827. Min Act: -0.0000

Data Index: 1208135 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.7511. Min Act: -0.0000

Data Index: 365376 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.7940. Min Act: -0.0000

Data Index: 1315823 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.7992. Min Act: -0.0000

Data Index: 1314204 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.7289. Min Act: -0.0000

Data Index: 1036921 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.7250. Min Act: -0.0000

Data Index: 48284 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.7562. Min Act: -0.0000

Data Index: 1207997 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.6815. Min Act: -0.0000

Data Index: 965700 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.7030. Min Act: -0.0000

Data Index: 404665 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.6630. Min Act: -0.0000

Data Index: 294146 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.6204. Min Act: -0.0000

Data Index: 934466 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.7058. Min Act: -0.0000

Data Index: 117105 (C4 (Web Text))

Max Activating Token Index: 798

Text #18

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.6948. Min Act: -0.0000

Data Index: 723659 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 1.0170. Min Range: -1.0170

Max Act: 0.6310. Min Act: -0.0000

Data Index: 444916 (C4 (Web Text))

Max Activating Token Index: 468