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

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

Neuron 4776 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: 1.6672. Min Range: -1.6672

Max Act: 1.6672. Min Act: -0.0003

Data Index: 1588415 (Python Code)

Max Activating Token Index: 182

Text #1

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.5926. Min Act: -0.0003

Data Index: 1362371 (Python Code)

Max Activating Token Index: 145

Text #2

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.5038. Min Act: -0.0003

Data Index: 1437632 (Python Code)

Max Activating Token Index: 59

Text #3

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.4584. Min Act: -0.0002

Data Index: 1422507 (Python Code)

Max Activating Token Index: 229

Text #4

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.3672. Min Act: -0.0003

Data Index: 1445794 (Python Code)

Max Activating Token Index: 441

Text #5

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.4349. Min Act: -0.0003

Data Index: 1519762 (Python Code)

Max Activating Token Index: 684

Text #6

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.3852. Min Act: -0.0003

Data Index: 1407983 (Python Code)

Max Activating Token Index: 258

Text #7

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.3767. Min Act: -0.0003

Data Index: 1529512 (Python Code)

Max Activating Token Index: 149

Text #8

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.3147. Min Act: -0.0003

Data Index: 1439153 (Python Code)

Max Activating Token Index: 123

Text #9

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.3245. Min Act: -0.0003

Data Index: 1582448 (Python Code)

Max Activating Token Index: 836

Text #10

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.3486. Min Act: -0.0002

Data Index: 1539147 (Python Code)

Max Activating Token Index: 818

Text #11

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.2655. Min Act: -0.0002

Data Index: 1642834 (Python Code)

Max Activating Token Index: 863

Text #12

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.2909. Min Act: -0.0003

Data Index: 1637835 (Python Code)

Max Activating Token Index: 100

Text #13

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.2854. Min Act: -0.0003

Data Index: 1363938 (Python Code)

Max Activating Token Index: 297

Text #14

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.2760. Min Act: -0.0003

Data Index: 1568421 (Python Code)

Max Activating Token Index: 60

Text #15

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.2056. Min Act: -0.0003

Data Index: 1614688 (Python Code)

Max Activating Token Index: 4

Text #16

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.1572. Min Act: -0.0003

Data Index: 1457838 (Python Code)

Max Activating Token Index: 267

Text #17

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.2182. Min Act: -0.0003

Data Index: 1430648 (Python Code)

Max Activating Token Index: 482

Text #18

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.2177. Min Act: -0.0003

Data Index: 1577191 (Python Code)

Max Activating Token Index: 350

Text #19

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.1762. Min Act: -0.0003

Data Index: 1501134 (Python Code)

Max Activating Token Index: 135