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

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

Neuron 4009 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6247. Min Range: -1.6247

Max Act: 1.6247. Min Act: 0.0001

Data Index: 1504887 (Python Code)

Max Activating Token Index: 313

Text #1

Max Range: 1.6247. Min Range: -1.6247

Max Act: 1.2960. Min Act: 0.0000

Data Index: 1637964 (Python Code)

Max Activating Token Index: 327

Text #2

Max Range: 1.6247. Min Range: -1.6247

Max Act: 1.3158. Min Act: 0.0000

Data Index: 1557090 (Python Code)

Max Activating Token Index: 834

Text #3

Max Range: 1.6247. Min Range: -1.6247

Max Act: 1.2799. Min Act: 0.0000

Data Index: 1457994 (Python Code)

Max Activating Token Index: 1018

Text #4

Max Range: 1.6247. Min Range: -1.6247

Max Act: 1.2182. Min Act: 0.0001

Data Index: 1586829 (Python Code)

Max Activating Token Index: 601

Text #5

Max Range: 1.6247. Min Range: -1.6247

Max Act: 1.1809. Min Act: 0.0001

Data Index: 1504037 (Python Code)

Max Activating Token Index: 133

Text #6

Max Range: 1.6247. Min Range: -1.6247

Max Act: 1.1901. Min Act: 0.0000

Data Index: 1544998 (Python Code)

Max Activating Token Index: 201

Text #7

Max Range: 1.6247. Min Range: -1.6247

Max Act: 1.0968. Min Act: 0.0000

Data Index: 1399143 (Python Code)

Max Activating Token Index: 191

Text #8

Max Range: 1.6247. Min Range: -1.6247

Max Act: 1.1578. Min Act: 0.0000

Data Index: 1446349 (Python Code)

Max Activating Token Index: 993

Text #9

Max Range: 1.6247. Min Range: -1.6247

Max Act: 1.1019. Min Act: -0.0000

Data Index: 1560064 (Python Code)

Max Activating Token Index: 1010

Text #10

Max Range: 1.6247. Min Range: -1.6247

Max Act: 1.0966. Min Act: 0.0000

Data Index: 1440985 (Python Code)

Max Activating Token Index: 34

Text #11

Max Range: 1.6247. Min Range: -1.6247

Max Act: 1.0909. Min Act: 0.0001

Data Index: 1445633 (Python Code)

Max Activating Token Index: 140

Text #12

Max Range: 1.6247. Min Range: -1.6247

Max Act: 1.0024. Min Act: 0.0000

Data Index: 1469577 (Python Code)

Max Activating Token Index: 986

Text #13

Max Range: 1.6247. Min Range: -1.6247

Max Act: 1.0601. Min Act: 0.0001

Data Index: 1531059 (Python Code)

Max Activating Token Index: 724

Text #14

Max Range: 1.6247. Min Range: -1.6247

Max Act: 1.0278. Min Act: 0.0000

Data Index: 1399971 (Python Code)

Max Activating Token Index: 971

Text #15

Max Range: 1.6247. Min Range: -1.6247

Max Act: 1.0294. Min Act: -0.0000

Data Index: 1425754 (Python Code)

Max Activating Token Index: 191

Text #16

Max Range: 1.6247. Min Range: -1.6247

Max Act: 0.9577. Min Act: 0.0000

Data Index: 1618652 (Python Code)

Max Activating Token Index: 310

Text #17

Max Range: 1.6247. Min Range: -1.6247

Max Act: 0.9915. Min Act: 0.0000

Data Index: 1555781 (Python Code)

Max Activating Token Index: 46

Text #18

Max Range: 1.6247. Min Range: -1.6247

Max Act: 0.9894. Min Act: 0.0001

Data Index: 1652961 (Python Code)

Max Activating Token Index: 874

Text #19

Max Range: 1.6247. Min Range: -1.6247

Max Act: 0.9502. Min Act: -0.0000

Data Index: 1403793 (Python Code)

Max Activating Token Index: 308