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

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

Neuron 650 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: 0.3876. Min Range: -0.3876

Max Act: 0.3876. Min Act: -0.0001

Data Index: 1119263 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.3234. Min Act: -0.0001

Data Index: 1237982 (C4 (Web Text))

Max Activating Token Index: 332

Text #2

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.3267. Min Act: -0.0001

Data Index: 380371 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.2977. Min Act: -0.0001

Data Index: 346519 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.3189. Min Act: -0.0001

Data Index: 254170 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.3060. Min Act: -0.0001

Data Index: 823103 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.3068. Min Act: -0.0001

Data Index: 1130078 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.2731. Min Act: -0.0001

Data Index: 801591 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.2782. Min Act: -0.0001

Data Index: 581404 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.2691. Min Act: -0.0001

Data Index: 333318 (C4 (Web Text))

Max Activating Token Index: 693

Text #10

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.2483. Min Act: -0.0001

Data Index: 1354872 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.2583. Min Act: -0.0001

Data Index: 1086641 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.2401. Min Act: -0.0001

Data Index: 182816 (C4 (Web Text))

Max Activating Token Index: 516

Text #13

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.2603. Min Act: -0.0001

Data Index: 1342864 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.2510. Min Act: -0.0001

Data Index: 616416 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.2594. Min Act: -0.0001

Data Index: 624914 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.2423. Min Act: -0.0001

Data Index: 823026 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.2525. Min Act: -0.0001

Data Index: 771073 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.2361. Min Act: -0.0001

Data Index: 821171 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.2510. Min Act: -0.0001

Data Index: 833555 (C4 (Web Text))

Max Activating Token Index: 147