Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3415 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 7.6457. Min Range: -7.6457

Max Act: 7.6457. Min Act: -0.0000

Data Index: 1533001 (Python Code)

Max Activating Token Index: 58

Text #1

Max Range: 7.6457. Min Range: -7.6457

Max Act: 7.4988. Min Act: -0.0000

Data Index: 1402887 (Python Code)

Max Activating Token Index: 92

Text #2

Max Range: 7.6457. Min Range: -7.6457

Max Act: 6.9916. Min Act: -0.0000

Data Index: 1598570 (Python Code)

Max Activating Token Index: 1021

Text #3

Max Range: 7.6457. Min Range: -7.6457

Max Act: 6.8739. Min Act: -0.0000

Data Index: 1553673 (Python Code)

Max Activating Token Index: 139

Text #4

Max Range: 7.6457. Min Range: -7.6457

Max Act: 6.9875. Min Act: -0.0000

Data Index: 1492610 (Python Code)

Max Activating Token Index: 209

Text #5

Max Range: 7.6457. Min Range: -7.6457

Max Act: 6.5260. Min Act: -0.0000

Data Index: 1598991 (Python Code)

Max Activating Token Index: 55

Text #6

Max Range: 7.6457. Min Range: -7.6457

Max Act: 6.4059. Min Act: -0.0000

Data Index: 1521981 (Python Code)

Max Activating Token Index: 107

Text #7

Max Range: 7.6457. Min Range: -7.6457

Max Act: 6.1762. Min Act: -0.0000

Data Index: 1502669 (Python Code)

Max Activating Token Index: 98

Text #8

Max Range: 7.6457. Min Range: -7.6457

Max Act: 6.1894. Min Act: -0.0000

Data Index: 1384501 (Python Code)

Max Activating Token Index: 983

Text #9

Max Range: 7.6457. Min Range: -7.6457

Max Act: 5.9642. Min Act: -0.0000

Data Index: 1592284 (Python Code)

Max Activating Token Index: 116

Text #10

Max Range: 7.6457. Min Range: -7.6457

Max Act: 5.8932. Min Act: -0.0000

Data Index: 1517920 (Python Code)

Max Activating Token Index: 21

Text #11

Max Range: 7.6457. Min Range: -7.6457

Max Act: 5.8865. Min Act: -0.0000

Data Index: 1389093 (Python Code)

Max Activating Token Index: 296

Text #12

Max Range: 7.6457. Min Range: -7.6457

Max Act: 5.6198. Min Act: -0.0000

Data Index: 1459598 (Python Code)

Max Activating Token Index: 115

Text #13

Max Range: 7.6457. Min Range: -7.6457

Max Act: 5.4706. Min Act: -0.0000

Data Index: 1420635 (Python Code)

Max Activating Token Index: 560

Text #14

Max Range: 7.6457. Min Range: -7.6457

Max Act: 5.4648. Min Act: -0.0000

Data Index: 1457656 (Python Code)

Max Activating Token Index: 284

Text #15

Max Range: 7.6457. Min Range: -7.6457

Max Act: 5.4116. Min Act: -0.0000

Data Index: 1641987 (Python Code)

Max Activating Token Index: 116

Text #16

Max Range: 7.6457. Min Range: -7.6457

Max Act: 5.3919. Min Act: -0.0000

Data Index: 1536269 (Python Code)

Max Activating Token Index: 60

Text #17

Max Range: 7.6457. Min Range: -7.6457

Max Act: 5.1767. Min Act: -0.0000

Data Index: 1486357 (Python Code)

Max Activating Token Index: 231

Text #18

Max Range: 7.6457. Min Range: -7.6457

Max Act: 5.2914. Min Act: -0.0000

Data Index: 1480934 (Python Code)

Max Activating Token Index: 24

Text #19

Max Range: 7.6457. Min Range: -7.6457

Max Act: 5.0965. Min Act: -0.0000

Data Index: 1429046 (Python Code)

Max Activating Token Index: 104