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

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

Neuron 2962 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.6875. Min Act: -0.0000

Data Index: 1548396 (Python Code)

Max Activating Token Index: 289

Text #1

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.6106. Min Act: -0.0000

Data Index: 1479151 (Python Code)

Max Activating Token Index: 343

Text #2

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5986. Min Act: -0.0000

Data Index: 1449644 (Python Code)

Max Activating Token Index: 353

Text #3

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5737. Min Act: -0.0000

Data Index: 1616772 (Python Code)

Max Activating Token Index: 218

Text #4

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.6031. Min Act: -0.0000

Data Index: 1424737 (Python Code)

Max Activating Token Index: 467

Text #5

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.6027. Min Act: -0.0000

Data Index: 1425369 (Python Code)

Max Activating Token Index: 430

Text #6

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5754. Min Act: -0.0000

Data Index: 1427580 (Python Code)

Max Activating Token Index: 156

Text #7

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5521. Min Act: -0.0000

Data Index: 1514788 (Python Code)

Max Activating Token Index: 538

Text #8

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.4973. Min Act: -0.0000

Data Index: 1574136 (Python Code)

Max Activating Token Index: 220

Text #9

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.4801. Min Act: -0.0000

Data Index: 1600282 (Python Code)

Max Activating Token Index: 219

Text #10

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.4804. Min Act: -0.0000

Data Index: 1438306 (Python Code)

Max Activating Token Index: 160

Text #11

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.4952. Min Act: -0.0000

Data Index: 1489207 (Python Code)

Max Activating Token Index: 193

Text #12

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.4632. Min Act: -0.0000

Data Index: 1378488 (Python Code)

Max Activating Token Index: 998

Text #13

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.4900. Min Act: -0.0000

Data Index: 1486628 (Python Code)

Max Activating Token Index: 32

Text #14

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.4880. Min Act: -0.0000

Data Index: 1481085 (Python Code)

Max Activating Token Index: 589

Text #15

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.4692. Min Act: -0.0000

Data Index: 1598746 (Python Code)

Max Activating Token Index: 688

Text #16

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.4865. Min Act: -0.0000

Data Index: 1500771 (Python Code)

Max Activating Token Index: 161

Text #17

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.4536. Min Act: -0.0000

Data Index: 1544074 (Python Code)

Max Activating Token Index: 252

Text #18

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.4535. Min Act: -0.0000

Data Index: 1522193 (Python Code)

Max Activating Token Index: 540

Text #19

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.4670. Min Act: -0.0000

Data Index: 1455132 (Python Code)

Max Activating Token Index: 468