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

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

Neuron 4167 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1434. Min Range: -1.1434

Max Act: 1.1434. Min Act: -0.0002

Data Index: 1161751 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 1.1434. Min Range: -1.1434

Max Act: 1.0467. Min Act: -0.0002

Data Index: 528599 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 1.1434. Min Range: -1.1434

Max Act: 1.0192. Min Act: -0.0002

Data Index: 1354639 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 1.1434. Min Range: -1.1434

Max Act: 0.8834. Min Act: -0.0002

Data Index: 133977 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 1.1434. Min Range: -1.1434

Max Act: 0.9084. Min Act: -0.0002

Data Index: 610436 (C4 (Web Text))

Max Activating Token Index: 495

Text #5

Max Range: 1.1434. Min Range: -1.1434

Max Act: 0.8556. Min Act: -0.0002

Data Index: 866927 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 1.1434. Min Range: -1.1434

Max Act: 0.8475. Min Act: -0.0002

Data Index: 843253 (C4 (Web Text))

Max Activating Token Index: 996

Text #7

Max Range: 1.1434. Min Range: -1.1434

Max Act: 0.7052. Min Act: -0.0002

Data Index: 272422 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 1.1434. Min Range: -1.1434

Max Act: 0.7892. Min Act: -0.0002

Data Index: 407220 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 1.1434. Min Range: -1.1434

Max Act: 0.8240. Min Act: -0.0002

Data Index: 249980 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 1.1434. Min Range: -1.1434

Max Act: 0.7549. Min Act: -0.0002

Data Index: 372609 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 1.1434. Min Range: -1.1434

Max Act: 0.7859. Min Act: -0.0002

Data Index: 303284 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 1.1434. Min Range: -1.1434

Max Act: 0.7624. Min Act: -0.0002

Data Index: 1353170 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 1.1434. Min Range: -1.1434

Max Act: 0.6984. Min Act: -0.0002

Data Index: 602953 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 1.1434. Min Range: -1.1434

Max Act: 0.6658. Min Act: -0.0002

Data Index: 1006731 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 1.1434. Min Range: -1.1434

Max Act: 0.7146. Min Act: -0.0002

Data Index: 41713 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 1.1434. Min Range: -1.1434

Max Act: 0.7314. Min Act: -0.0002

Data Index: 604500 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 1.1434. Min Range: -1.1434

Max Act: 0.6672. Min Act: -0.0002

Data Index: 191678 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 1.1434. Min Range: -1.1434

Max Act: 0.7070. Min Act: -0.0002

Data Index: 939225 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 1.1434. Min Range: -1.1434

Max Act: 0.6235. Min Act: -0.0002

Data Index: 112801 (C4 (Web Text))

Max Activating Token Index: 146