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

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

Neuron 1638 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.2985. Min Act: -0.0000

Data Index: 1250765 (C4 (Web Text))

Max Activating Token Index: 805

Text #1

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.3245. Min Act: -0.0000

Data Index: 1118970 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.2960. Min Act: -0.0000

Data Index: 999262 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.2985. Min Act: -0.0000

Data Index: 10740 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.2955. Min Act: -0.0000

Data Index: 1261404 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.3444. Min Act: -0.0000

Data Index: 812466 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.2995. Min Act: -0.0000

Data Index: 1178474 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.2867. Min Act: -0.0000

Data Index: 1138457 (C4 (Web Text))

Max Activating Token Index: 266

Text #8

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.2732. Min Act: -0.0000

Data Index: 1087836 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.2924. Min Act: -0.0000

Data Index: 1281074 (C4 (Web Text))

Max Activating Token Index: 767

Text #10

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.2677. Min Act: -0.0000

Data Index: 680163 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.2594. Min Act: -0.0000

Data Index: 811058 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.2521. Min Act: -0.0000

Data Index: 913400 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.2848. Min Act: -0.0000

Data Index: 1056189 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.2841. Min Act: -0.0000

Data Index: 924244 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.2951. Min Act: -0.0000

Data Index: 475267 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.2628. Min Act: -0.0000

Data Index: 1063353 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.2453. Min Act: -0.0000

Data Index: 1244068 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.2537. Min Act: -0.0000

Data Index: 621457 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.2631. Min Act: -0.0000

Data Index: 1000731 (C4 (Web Text))

Max Activating Token Index: 770