Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5163 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7398. Min Range: -2.7398

Max Act: 2.7398. Min Act: -0.0000

Data Index: 1181836 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 2.7398. Min Range: -2.7398

Max Act: 2.5912. Min Act: -0.0000

Data Index: 577053 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 2.7398. Min Range: -2.7398

Max Act: 2.3082. Min Act: -0.0000

Data Index: 410742 (C4 (Web Text))

Max Activating Token Index: 627

Text #3

Max Range: 2.7398. Min Range: -2.7398

Max Act: 2.2096. Min Act: -0.0000

Data Index: 1092984 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 2.7398. Min Range: -2.7398

Max Act: 2.1937. Min Act: -0.0000

Data Index: 694202 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 2.7398. Min Range: -2.7398

Max Act: 2.0767. Min Act: -0.0000

Data Index: 1266963 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 2.7398. Min Range: -2.7398

Max Act: 2.0434. Min Act: -0.0000

Data Index: 641038 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 2.7398. Min Range: -2.7398

Max Act: 2.2693. Min Act: -0.0000

Data Index: 472019 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 2.7398. Min Range: -2.7398

Max Act: 1.9937. Min Act: -0.0000

Data Index: 179865 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 2.7398. Min Range: -2.7398

Max Act: 2.1029. Min Act: -0.0000

Data Index: 279351 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 2.7398. Min Range: -2.7398

Max Act: 1.9282. Min Act: -0.0000

Data Index: 1274630 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 2.7398. Min Range: -2.7398

Max Act: 2.2477. Min Act: -0.0000

Data Index: 333082 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 2.7398. Min Range: -2.7398

Max Act: 1.6080. Min Act: -0.0000

Data Index: 1155781 (C4 (Web Text))

Max Activating Token Index: 309

Text #13

Max Range: 2.7398. Min Range: -2.7398

Max Act: 2.0979. Min Act: -0.0000

Data Index: 190137 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 2.7398. Min Range: -2.7398

Max Act: 1.9231. Min Act: -0.0000

Data Index: 77853 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 2.7398. Min Range: -2.7398

Max Act: 1.6979. Min Act: -0.0000

Data Index: 1079923 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 2.7398. Min Range: -2.7398

Max Act: 1.8544. Min Act: -0.0000

Data Index: 225711 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 2.7398. Min Range: -2.7398

Max Act: 1.7571. Min Act: -0.0000

Data Index: 793455 (C4 (Web Text))

Max Activating Token Index: 322

Text #18

Max Range: 2.7398. Min Range: -2.7398

Max Act: 1.7753. Min Act: -0.0000

Data Index: 909244 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 2.7398. Min Range: -2.7398

Max Act: 1.8322. Min Act: -0.0000

Data Index: 493782 (C4 (Web Text))

Max Activating Token Index: 702