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

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

Neuron 4459 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6420. Min Range: -1.6420

Max Act: 1.6420. Min Act: -0.0002

Data Index: 1333667 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 1.6420. Min Range: -1.6420

Max Act: 1.4707. Min Act: -0.0002

Data Index: 156860 (C4 (Web Text))

Max Activating Token Index: 295

Text #2

Max Range: 1.6420. Min Range: -1.6420

Max Act: 1.1482. Min Act: -0.0002

Data Index: 12519 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 1.6420. Min Range: -1.6420

Max Act: 1.1322. Min Act: -0.0002

Data Index: 1005673 (C4 (Web Text))

Max Activating Token Index: 1019

Text #4

Max Range: 1.6420. Min Range: -1.6420

Max Act: 1.0806. Min Act: -0.0002

Data Index: 725459 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 1.6420. Min Range: -1.6420

Max Act: 1.0929. Min Act: -0.0002

Data Index: 120304 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 1.6420. Min Range: -1.6420

Max Act: 1.0006. Min Act: -0.0002

Data Index: 176789 (C4 (Web Text))

Max Activating Token Index: 94

Text #7

Max Range: 1.6420. Min Range: -1.6420

Max Act: 0.9014. Min Act: -0.0002

Data Index: 843557 (C4 (Web Text))

Max Activating Token Index: 254

Text #8

Max Range: 1.6420. Min Range: -1.6420

Max Act: 0.8647. Min Act: -0.0002

Data Index: 1321645 (C4 (Web Text))

Max Activating Token Index: 446

Text #9

Max Range: 1.6420. Min Range: -1.6420

Max Act: 0.8544. Min Act: -0.0002

Data Index: 757910 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 1.6420. Min Range: -1.6420

Max Act: 0.9091. Min Act: -0.0002

Data Index: 1035347 (C4 (Web Text))

Max Activating Token Index: 165

Text #11

Max Range: 1.6420. Min Range: -1.6420

Max Act: 0.8008. Min Act: -0.0002

Data Index: 997670 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 1.6420. Min Range: -1.6420

Max Act: 0.8161. Min Act: -0.0002

Data Index: 774030 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 1.6420. Min Range: -1.6420

Max Act: 0.8335. Min Act: -0.0002

Data Index: 920850 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 1.6420. Min Range: -1.6420

Max Act: 0.8745. Min Act: -0.0002

Data Index: 300308 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 1.6420. Min Range: -1.6420

Max Act: 0.7758. Min Act: -0.0002

Data Index: 422066 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 1.6420. Min Range: -1.6420

Max Act: 0.7428. Min Act: -0.0002

Data Index: 107241 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 1.6420. Min Range: -1.6420

Max Act: 0.7573. Min Act: -0.0002

Data Index: 1268316 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 1.6420. Min Range: -1.6420

Max Act: 0.7229. Min Act: -0.0002

Data Index: 712188 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 1.6420. Min Range: -1.6420

Max Act: 0.7303. Min Act: -0.0002

Data Index: 767964 (C4 (Web Text))

Max Activating Token Index: 753