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

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

Neuron 72 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: 1.4334. Min Range: -1.4334

Max Act: 1.4334. Min Act: -0.0002

Data Index: 158570 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 1.4334. Min Range: -1.4334

Max Act: 1.3593. Min Act: -0.0002

Data Index: 630308 (C4 (Web Text))

Max Activating Token Index: 741

Text #2

Max Range: 1.4334. Min Range: -1.4334

Max Act: 1.2536. Min Act: -0.0002

Data Index: 110800 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 1.4334. Min Range: -1.4334

Max Act: 1.2741. Min Act: -0.0002

Data Index: 743564 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 1.4334. Min Range: -1.4334

Max Act: 1.2428. Min Act: -0.0002

Data Index: 760568 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 1.4334. Min Range: -1.4334

Max Act: 1.2609. Min Act: -0.0003

Data Index: 417169 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 1.4334. Min Range: -1.4334

Max Act: 1.2426. Min Act: -0.0002

Data Index: 986382 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 1.4334. Min Range: -1.4334

Max Act: 1.2367. Min Act: -0.0002

Data Index: 1073686 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 1.4334. Min Range: -1.4334

Max Act: 1.1997. Min Act: -0.0002

Data Index: 1057374 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 1.4334. Min Range: -1.4334

Max Act: 1.1731. Min Act: -0.0002

Data Index: 111264 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 1.4334. Min Range: -1.4334

Max Act: 1.1698. Min Act: -0.0002

Data Index: 255887 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 1.4334. Min Range: -1.4334

Max Act: 1.1375. Min Act: -0.0002

Data Index: 917011 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 1.4334. Min Range: -1.4334

Max Act: 1.1374. Min Act: -0.0002

Data Index: 1123496 (C4 (Web Text))

Max Activating Token Index: 2

Text #13

Max Range: 1.4334. Min Range: -1.4334

Max Act: 1.1447. Min Act: -0.0002

Data Index: 793032 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 1.4334. Min Range: -1.4334

Max Act: 1.1419. Min Act: -0.0002

Data Index: 155487 (C4 (Web Text))

Max Activating Token Index: 328

Text #15

Max Range: 1.4334. Min Range: -1.4334

Max Act: 1.1248. Min Act: -0.0002

Data Index: 258414 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 1.4334. Min Range: -1.4334

Max Act: 1.1385. Min Act: -0.0002

Data Index: 985610 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 1.4334. Min Range: -1.4334

Max Act: 1.1088. Min Act: -0.0003

Data Index: 146347 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 1.4334. Min Range: -1.4334

Max Act: 1.1159. Min Act: -0.0002

Data Index: 280542 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 1.4334. Min Range: -1.4334

Max Act: 1.1114. Min Act: -0.0002

Data Index: 392865 (C4 (Web Text))

Max Activating Token Index: 981