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

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

Neuron 2976 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.8242. Min Act: -0.0003

Data Index: 34558 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.8203. Min Act: -0.0003

Data Index: 160451 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7914. Min Act: -0.0002

Data Index: 478930 (C4 (Web Text))

Max Activating Token Index: 587

Text #3

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7946. Min Act: -0.0003

Data Index: 349891 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7549. Min Act: -0.0002

Data Index: 1052841 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7548. Min Act: -0.0002

Data Index: 662227 (C4 (Web Text))

Max Activating Token Index: 422

Text #6

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7763. Min Act: -0.0003

Data Index: 1034696 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7230. Min Act: -0.0003

Data Index: 1237148 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7425. Min Act: -0.0002

Data Index: 967401 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7330. Min Act: -0.0003

Data Index: 536567 (C4 (Web Text))

Max Activating Token Index: 400

Text #10

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7080. Min Act: -0.0003

Data Index: 1157135 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7260. Min Act: -0.0003

Data Index: 810952 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7225. Min Act: -0.0002

Data Index: 316836 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7100. Min Act: -0.0003

Data Index: 1051356 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.6965. Min Act: -0.0003

Data Index: 141110 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.6968. Min Act: -0.0003

Data Index: 1162309 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.6975. Min Act: -0.0003

Data Index: 26972 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.6727. Min Act: -0.0002

Data Index: 447656 (C4 (Web Text))

Max Activating Token Index: 378

Text #18

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.6672. Min Act: -0.0002

Data Index: 90273 (C4 (Web Text))

Max Activating Token Index: 204

Text #19

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.6879. Min Act: -0.0002

Data Index: 547633 (C4 (Web Text))

Max Activating Token Index: 294