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

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

Neuron 2397 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2801. Min Act: -0.0001

Data Index: 328514 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2950. Min Act: -0.0001

Data Index: 1079720 (C4 (Web Text))

Max Activating Token Index: 311

Text #2

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2821. Min Act: -0.0001

Data Index: 368791 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2777. Min Act: -0.0001

Data Index: 64329 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2680. Min Act: -0.0001

Data Index: 780518 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2660. Min Act: -0.0001

Data Index: 1096054 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2756. Min Act: -0.0001

Data Index: 1210692 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2561. Min Act: -0.0001

Data Index: 907175 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2560. Min Act: -0.0001

Data Index: 1238837 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2724. Min Act: -0.0001

Data Index: 773927 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2527. Min Act: -0.0001

Data Index: 729659 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2599. Min Act: -0.0001

Data Index: 937439 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2419. Min Act: -0.0001

Data Index: 94384 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2417. Min Act: -0.0001

Data Index: 184855 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2381. Min Act: -0.0001

Data Index: 1017362 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2370. Min Act: -0.0001

Data Index: 1258331 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2359. Min Act: -0.0001

Data Index: 1282014 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2407. Min Act: -0.0001

Data Index: 779213 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2330. Min Act: -0.0001

Data Index: 355069 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2234. Min Act: -0.0001

Data Index: 1001777 (C4 (Web Text))

Max Activating Token Index: 86