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

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

Neuron 3724 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.4302. Min Act: -0.0000

Data Index: 1256062 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.3451. Min Act: -0.0000

Data Index: 1268464 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.3205. Min Act: -0.0000

Data Index: 144666 (C4 (Web Text))

Max Activating Token Index: 395

Text #3

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.2706. Min Act: -0.0000

Data Index: 434122 (C4 (Web Text))

Max Activating Token Index: 949

Text #4

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.2939. Min Act: -0.0000

Data Index: 922311 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.2530. Min Act: -0.0000

Data Index: 499869 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.2596. Min Act: -0.0000

Data Index: 1117892 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.2584. Min Act: -0.0000

Data Index: 889673 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.2408. Min Act: -0.0000

Data Index: 315008 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.2396. Min Act: 0.0000

Data Index: 962872 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.2262. Min Act: -0.0000

Data Index: 724889 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.2151. Min Act: -0.0000

Data Index: 544248 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.2117. Min Act: -0.0000

Data Index: 1200577 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.2029. Min Act: 0.0000

Data Index: 839974 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.2017. Min Act: 0.0001

Data Index: 1311693 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.1957. Min Act: -0.0000

Data Index: 632902 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.1850. Min Act: -0.0000

Data Index: 664718 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.1931. Min Act: -0.0000

Data Index: 219194 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.1969. Min Act: -0.0000

Data Index: 592917 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.1832. Min Act: -0.0000

Data Index: 1177617 (C4 (Web Text))

Max Activating Token Index: 978