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

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

Neuron 1498 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.3290. Min Act: -0.0000

Data Index: 920663 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.3218. Min Act: -0.0000

Data Index: 398879 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.3034. Min Act: -0.0000

Data Index: 499843 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2955. Min Act: -0.0000

Data Index: 1285853 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2760. Min Act: -0.0000

Data Index: 655897 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2801. Min Act: -0.0000

Data Index: 905076 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2639. Min Act: -0.0000

Data Index: 503643 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2398. Min Act: -0.0000

Data Index: 1147416 (C4 (Web Text))

Max Activating Token Index: 905

Text #8

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2023. Min Act: -0.0000

Data Index: 715758 (C4 (Web Text))

Max Activating Token Index: 141

Text #9

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2203. Min Act: -0.0000

Data Index: 278476 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2021. Min Act: -0.0000

Data Index: 193951 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2002. Min Act: -0.0000

Data Index: 567789 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2024. Min Act: -0.0000

Data Index: 1131126 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.1883. Min Act: -0.0000

Data Index: 938149 (C4 (Web Text))

Max Activating Token Index: 211

Text #14

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.1854. Min Act: -0.0000

Data Index: 1244027 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.1770. Min Act: -0.0000

Data Index: 625466 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.1927. Min Act: -0.0000

Data Index: 1277119 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.1848. Min Act: -0.0000

Data Index: 444401 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.1807. Min Act: -0.0000

Data Index: 372189 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.1664. Min Act: -0.0000

Data Index: 181168 (C4 (Web Text))

Max Activating Token Index: 907