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

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

Neuron 1244 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: 0.3946. Min Range: -0.3946

Max Act: 0.3946. Min Act: -0.0001

Data Index: 386465 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3034. Min Act: -0.0001

Data Index: 90188 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.2787. Min Act: -0.0001

Data Index: 596556 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.2596. Min Act: -0.0001

Data Index: 1175313 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.2765. Min Act: -0.0001

Data Index: 266192 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.2752. Min Act: -0.0001

Data Index: 1980 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.2726. Min Act: -0.0001

Data Index: 1067781 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.2454. Min Act: -0.0001

Data Index: 937428 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.2698. Min Act: -0.0001

Data Index: 113971 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.2692. Min Act: -0.0001

Data Index: 428077 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.2651. Min Act: -0.0001

Data Index: 685770 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.2619. Min Act: -0.0001

Data Index: 531354 (C4 (Web Text))

Max Activating Token Index: 515

Text #12

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.2550. Min Act: -0.0001

Data Index: 1249835 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.2558. Min Act: -0.0001

Data Index: 314722 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.2605. Min Act: -0.0001

Data Index: 68231 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.2687. Min Act: -0.0001

Data Index: 640515 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.2634. Min Act: -0.0001

Data Index: 42716 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.2527. Min Act: -0.0001

Data Index: 648347 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.2432. Min Act: -0.0000

Data Index: 422137 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.2501. Min Act: -0.0001

Data Index: 772917 (C4 (Web Text))

Max Activating Token Index: 285