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

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

Neuron 4107 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.7379. Min Act: -0.0000

Data Index: 1508172 (Python Code)

Max Activating Token Index: 236

Text #1

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.7643. Min Act: -0.0001

Data Index: 1651868 (Python Code)

Max Activating Token Index: 346

Text #2

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.6844. Min Act: -0.0001

Data Index: 1381000 (Python Code)

Max Activating Token Index: 193

Text #3

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.5283. Min Act: -0.0000

Data Index: 1483923 (Python Code)

Max Activating Token Index: 232

Text #4

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.6806. Min Act: -0.0000

Data Index: 1524083 (Python Code)

Max Activating Token Index: 37

Text #5

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.6470. Min Act: -0.0001

Data Index: 1605389 (Python Code)

Max Activating Token Index: 179

Text #6

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.5879. Min Act: -0.0001

Data Index: 1603226 (Python Code)

Max Activating Token Index: 193

Text #7

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.4868. Min Act: -0.0001

Data Index: 1551378 (Python Code)

Max Activating Token Index: 578

Text #8

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.5229. Min Act: -0.0000

Data Index: 1595266 (Python Code)

Max Activating Token Index: 216

Text #9

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.5615. Min Act: -0.0001

Data Index: 1567522 (Python Code)

Max Activating Token Index: 24

Text #10

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.5664. Min Act: -0.0001

Data Index: 1423998 (Python Code)

Max Activating Token Index: 273

Text #11

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.4798. Min Act: -0.0001

Data Index: 1429533 (Python Code)

Max Activating Token Index: 21

Text #12

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.4727. Min Act: -0.0001

Data Index: 1550436 (Python Code)

Max Activating Token Index: 279

Text #13

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.4564. Min Act: -0.0000

Data Index: 1458206 (Python Code)

Max Activating Token Index: 207

Text #14

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.5004. Min Act: -0.0000

Data Index: 1532535 (Python Code)

Max Activating Token Index: 541

Text #15

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.4586. Min Act: -0.0000

Data Index: 1574739 (Python Code)

Max Activating Token Index: 214

Text #16

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.4995. Min Act: -0.0000

Data Index: 1500873 (Python Code)

Max Activating Token Index: 265

Text #17

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.4505. Min Act: -0.0000

Data Index: 1465031 (Python Code)

Max Activating Token Index: 62

Text #18

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.5307. Min Act: -0.0001

Data Index: 1512655 (Python Code)

Max Activating Token Index: 130

Text #19

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.4433. Min Act: -0.0001

Data Index: 1637185 (Python Code)

Max Activating Token Index: 21