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

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

Neuron 4458 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: 1.9824. Min Range: -1.9824

Max Act: 1.9617. Min Act: -0.0002

Data Index: 1438127 (Python Code)

Max Activating Token Index: 81

Text #1

Max Range: 1.9824. Min Range: -1.9824

Max Act: 1.9824. Min Act: -0.0002

Data Index: 1400398 (Python Code)

Max Activating Token Index: 41

Text #2

Max Range: 1.9824. Min Range: -1.9824

Max Act: 1.8164. Min Act: -0.0002

Data Index: 1566643 (Python Code)

Max Activating Token Index: 811

Text #3

Max Range: 1.9824. Min Range: -1.9824

Max Act: 1.7715. Min Act: -0.0002

Data Index: 1521668 (Python Code)

Max Activating Token Index: 9

Text #4

Max Range: 1.9824. Min Range: -1.9824

Max Act: 1.9034. Min Act: -0.0002

Data Index: 1436241 (Python Code)

Max Activating Token Index: 26

Text #5

Max Range: 1.9824. Min Range: -1.9824

Max Act: 1.6783. Min Act: -0.0002

Data Index: 1621177 (Python Code)

Max Activating Token Index: 193

Text #6

Max Range: 1.9824. Min Range: -1.9824

Max Act: 1.9038. Min Act: -0.0002

Data Index: 1578612 (Python Code)

Max Activating Token Index: 291

Text #7

Max Range: 1.9824. Min Range: -1.9824

Max Act: 1.7036. Min Act: -0.0002

Data Index: 1407657 (Python Code)

Max Activating Token Index: 61

Text #8

Max Range: 1.9824. Min Range: -1.9824

Max Act: 1.7813. Min Act: -0.0002

Data Index: 1566377 (Python Code)

Max Activating Token Index: 570

Text #9

Max Range: 1.9824. Min Range: -1.9824

Max Act: 1.8282. Min Act: -0.0002

Data Index: 1637328 (Python Code)

Max Activating Token Index: 25

Text #10

Max Range: 1.9824. Min Range: -1.9824

Max Act: 1.8077. Min Act: -0.0002

Data Index: 1532590 (Python Code)

Max Activating Token Index: 8

Text #11

Max Range: 1.9824. Min Range: -1.9824

Max Act: 1.6681. Min Act: -0.0002

Data Index: 1612316 (Python Code)

Max Activating Token Index: 33

Text #12

Max Range: 1.9824. Min Range: -1.9824

Max Act: 1.7037. Min Act: -0.0002

Data Index: 1570597 (Python Code)

Max Activating Token Index: 10

Text #13

Max Range: 1.9824. Min Range: -1.9824

Max Act: 1.7451. Min Act: -0.0002

Data Index: 1537147 (Python Code)

Max Activating Token Index: 358

Text #14

Max Range: 1.9824. Min Range: -1.9824

Max Act: 1.6334. Min Act: -0.0002

Data Index: 1441828 (Python Code)

Max Activating Token Index: 69

Text #15

Max Range: 1.9824. Min Range: -1.9824

Max Act: 1.3655. Min Act: -0.0002

Data Index: 1641918 (Python Code)

Max Activating Token Index: 784

Text #16

Max Range: 1.9824. Min Range: -1.9824

Max Act: 1.9190. Min Act: -0.0002

Data Index: 1364189 (Python Code)

Max Activating Token Index: 29

Text #17

Max Range: 1.9824. Min Range: -1.9824

Max Act: 1.5877. Min Act: -0.0002

Data Index: 1421605 (Python Code)

Max Activating Token Index: 112

Text #18

Max Range: 1.9824. Min Range: -1.9824

Max Act: 1.8608. Min Act: -0.0002

Data Index: 1598969 (Python Code)

Max Activating Token Index: 122

Text #19

Max Range: 1.9824. Min Range: -1.9824

Max Act: 1.4979. Min Act: -0.0002

Data Index: 1656799 (Python Code)

Max Activating Token Index: 151