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

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

Neuron 1089 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.8245. Min Act: -0.0003

Data Index: 397185 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.7451. Min Act: -0.0003

Data Index: 1106848 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.7066. Min Act: -0.0003

Data Index: 1039107 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.6471. Min Act: -0.0003

Data Index: 1314309 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.7150. Min Act: -0.0003

Data Index: 92355 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.6128. Min Act: -0.0003

Data Index: 1270228 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.6091. Min Act: -0.0003

Data Index: 1269750 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.5233. Min Act: -0.0003

Data Index: 685758 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.6139. Min Act: -0.0003

Data Index: 1320739 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.5594. Min Act: -0.0003

Data Index: 350900 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.5709. Min Act: -0.0003

Data Index: 178142 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.5454. Min Act: -0.0003

Data Index: 177315 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.4813. Min Act: -0.0003

Data Index: 907149 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.5956. Min Act: -0.0003

Data Index: 703905 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.6429. Min Act: -0.0003

Data Index: 1070510 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.5306. Min Act: -0.0003

Data Index: 318087 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.5465. Min Act: -0.0003

Data Index: 962309 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.5817. Min Act: -0.0003

Data Index: 737355 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.5951. Min Act: -0.0003

Data Index: 281812 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.5906. Min Act: -0.0003

Data Index: 79649 (C4 (Web Text))

Max Activating Token Index: 966