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

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

Neuron 970 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: 1.2779. Min Range: -1.2779

Max Act: 1.2779. Min Act: -0.0002

Data Index: 181725 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 1.2779. Min Range: -1.2779

Max Act: 1.2414. Min Act: -0.0002

Data Index: 707108 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 1.2779. Min Range: -1.2779

Max Act: 1.2414. Min Act: -0.0002

Data Index: 1504134 (Python Code)

Max Activating Token Index: 2

Text #3

Max Range: 1.2779. Min Range: -1.2779

Max Act: 1.2414. Min Act: -0.0002

Data Index: 712552 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 1.2779. Min Range: -1.2779

Max Act: 1.2414. Min Act: -0.0002

Data Index: 761532 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 1.2779. Min Range: -1.2779

Max Act: 1.2279. Min Act: -0.0002

Data Index: 634619 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 1.2779. Min Range: -1.2779

Max Act: 1.1792. Min Act: -0.0002

Data Index: 1138166 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 1.2779. Min Range: -1.2779

Max Act: 1.1434. Min Act: -0.0002

Data Index: 309288 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 1.2779. Min Range: -1.2779

Max Act: 1.1532. Min Act: -0.0002

Data Index: 546769 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 1.2779. Min Range: -1.2779

Max Act: 1.1211. Min Act: -0.0002

Data Index: 737316 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 1.2779. Min Range: -1.2779

Max Act: 1.1233. Min Act: -0.0002

Data Index: 471544 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 1.2779. Min Range: -1.2779

Max Act: 1.1014. Min Act: -0.0002

Data Index: 1026761 (C4 (Web Text))

Max Activating Token Index: 828

Text #12

Max Range: 1.2779. Min Range: -1.2779

Max Act: 1.0693. Min Act: -0.0002

Data Index: 944674 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 1.2779. Min Range: -1.2779

Max Act: 1.0963. Min Act: -0.0002

Data Index: 1324844 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 1.2779. Min Range: -1.2779

Max Act: 1.0846. Min Act: -0.0002

Data Index: 555573 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 1.2779. Min Range: -1.2779

Max Act: 1.0982. Min Act: -0.0002

Data Index: 1324884 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 1.2779. Min Range: -1.2779

Max Act: 1.1169. Min Act: -0.0002

Data Index: 315041 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 1.2779. Min Range: -1.2779

Max Act: 1.0770. Min Act: -0.0002

Data Index: 102107 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 1.2779. Min Range: -1.2779

Max Act: 1.0877. Min Act: -0.0002

Data Index: 54299 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 1.2779. Min Range: -1.2779

Max Act: 1.0792. Min Act: -0.0002

Data Index: 1290673 (C4 (Web Text))

Max Activating Token Index: 65