Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 249 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.4262. Min Act: -0.0001

Data Index: 1023011 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.2826. Min Act: -0.0001

Data Index: 1116697 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.2938. Min Act: -0.0001

Data Index: 141078 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.2919. Min Act: -0.0001

Data Index: 611424 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.2646. Min Act: -0.0001

Data Index: 122512 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.2639. Min Act: -0.0000

Data Index: 1159555 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.2692. Min Act: -0.0001

Data Index: 963644 (C4 (Web Text))

Max Activating Token Index: 506

Text #7

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.2694. Min Act: -0.0001

Data Index: 940054 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.2682. Min Act: -0.0001

Data Index: 656159 (C4 (Web Text))

Max Activating Token Index: 355

Text #9

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.2537. Min Act: -0.0001

Data Index: 48520 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.2888. Min Act: -0.0001

Data Index: 698507 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.2784. Min Act: -0.0001

Data Index: 568835 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.2652. Min Act: -0.0001

Data Index: 53659 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.2396. Min Act: -0.0001

Data Index: 920791 (C4 (Web Text))

Max Activating Token Index: 343

Text #14

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.2103. Min Act: -0.0001

Data Index: 839628 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.2488. Min Act: -0.0001

Data Index: 885579 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.2515. Min Act: -0.0001

Data Index: 584614 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.2575. Min Act: -0.0001

Data Index: 40948 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.2423. Min Act: -0.0001

Data Index: 687359 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.2484. Min Act: -0.0001

Data Index: 748094 (C4 (Web Text))

Max Activating Token Index: 83