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

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

Neuron 1125 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0294. Min Act: -0.0002

Data Index: 65591 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0271. Min Act: -0.0002

Data Index: 1080580 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0237. Min Act: -0.0002

Data Index: 495840 (C4 (Web Text))

Max Activating Token Index: 633

Text #3

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0231. Min Act: -0.0002

Data Index: 664143 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0214. Min Act: -0.0002

Data Index: 80159 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0211. Min Act: -0.0002

Data Index: 422309 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0214. Min Act: -0.0002

Data Index: 877516 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0218. Min Act: -0.0002

Data Index: 409841 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0211. Min Act: -0.0002

Data Index: 626410 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0209. Min Act: -0.0002

Data Index: 48892 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0211. Min Act: -0.0002

Data Index: 787477 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0213. Min Act: -0.0002

Data Index: 1141008 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0206. Min Act: -0.0002

Data Index: 868897 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0214. Min Act: -0.0002

Data Index: 718868 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0200. Min Act: -0.0002

Data Index: 875509 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0203. Min Act: -0.0002

Data Index: 684351 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0189. Min Act: -0.0002

Data Index: 693773 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0201. Min Act: -0.0002

Data Index: 663349 (C4 (Web Text))

Max Activating Token Index: 478

Text #18

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1064747 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0193. Min Act: -0.0002

Data Index: 359934 (C4 (Web Text))

Max Activating Token Index: 745