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

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

Neuron 548 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2121. Min Range: -1.2121

Max Act: 1.2121. Min Act: -0.0000

Data Index: 1604349 (Python Code)

Max Activating Token Index: 567

Text #1

Max Range: 1.2121. Min Range: -1.2121

Max Act: 1.1380. Min Act: -0.0000

Data Index: 1395756 (Python Code)

Max Activating Token Index: 973

Text #2

Max Range: 1.2121. Min Range: -1.2121

Max Act: 1.0282. Min Act: -0.0000

Data Index: 1509208 (Python Code)

Max Activating Token Index: 741

Text #3

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.9862. Min Act: -0.0000

Data Index: 1379896 (Python Code)

Max Activating Token Index: 178

Text #4

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.9370. Min Act: -0.0000

Data Index: 1428151 (Python Code)

Max Activating Token Index: 170

Text #5

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.9974. Min Act: -0.0000

Data Index: 1607974 (Python Code)

Max Activating Token Index: 180

Text #6

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.8926. Min Act: -0.0000

Data Index: 629684 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.8017. Min Act: -0.0000

Data Index: 1459222 (Python Code)

Max Activating Token Index: 523

Text #8

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.8098. Min Act: -0.0000

Data Index: 1488783 (Python Code)

Max Activating Token Index: 984

Text #9

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.7427. Min Act: -0.0000

Data Index: 1459003 (Python Code)

Max Activating Token Index: 444

Text #10

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.7301. Min Act: -0.0000

Data Index: 1615149 (Python Code)

Max Activating Token Index: 85

Text #11

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.7826. Min Act: -0.0000

Data Index: 1542067 (Python Code)

Max Activating Token Index: 714

Text #12

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.7368. Min Act: -0.0000

Data Index: 1408768 (Python Code)

Max Activating Token Index: 223

Text #13

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.7295. Min Act: -0.0000

Data Index: 1609741 (Python Code)

Max Activating Token Index: 197

Text #14

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.7141. Min Act: -0.0000

Data Index: 1632093 (Python Code)

Max Activating Token Index: 493

Text #15

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.7366. Min Act: -0.0000

Data Index: 1460139 (Python Code)

Max Activating Token Index: 91

Text #16

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.7057. Min Act: -0.0000

Data Index: 1529447 (Python Code)

Max Activating Token Index: 617

Text #17

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.7135. Min Act: -0.0000

Data Index: 1551521 (Python Code)

Max Activating Token Index: 490

Text #18

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.7090. Min Act: -0.0000

Data Index: 1540201 (Python Code)

Max Activating Token Index: 206

Text #19

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.6499. Min Act: -0.0000

Data Index: 1602020 (Python Code)

Max Activating Token Index: 736