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

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

Neuron 1288 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: 0.8872. Min Range: -0.8872

Max Act: 0.8872. Min Act: -0.0000

Data Index: 1646737 (Python Code)

Max Activating Token Index: 218

Text #1

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.8798. Min Act: -0.0000

Data Index: 1470707 (Python Code)

Max Activating Token Index: 144

Text #2

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.7808. Min Act: -0.0000

Data Index: 1645229 (Python Code)

Max Activating Token Index: 555

Text #3

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.6402. Min Act: -0.0000

Data Index: 1512340 (Python Code)

Max Activating Token Index: 428

Text #4

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.6271. Min Act: 0.0000

Data Index: 1493563 (Python Code)

Max Activating Token Index: 28

Text #5

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.6192. Min Act: 0.0001

Data Index: 1611091 (Python Code)

Max Activating Token Index: 150

Text #6

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.5933. Min Act: -0.0000

Data Index: 1480294 (Python Code)

Max Activating Token Index: 424

Text #7

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.6099. Min Act: -0.0000

Data Index: 1426981 (Python Code)

Max Activating Token Index: 716

Text #8

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.5996. Min Act: -0.0000

Data Index: 1530812 (Python Code)

Max Activating Token Index: 207

Text #9

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.5712. Min Act: -0.0000

Data Index: 1469808 (Python Code)

Max Activating Token Index: 740

Text #10

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.6118. Min Act: -0.0000

Data Index: 1510790 (Python Code)

Max Activating Token Index: 178

Text #11

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.6068. Min Act: -0.0000

Data Index: 1391438 (Python Code)

Max Activating Token Index: 511

Text #12

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.5848. Min Act: 0.0001

Data Index: 1381829 (Python Code)

Max Activating Token Index: 353

Text #13

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.6014. Min Act: 0.0000

Data Index: 1566661 (Python Code)

Max Activating Token Index: 1002

Text #14

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.5742. Min Act: -0.0000

Data Index: 1591857 (Python Code)

Max Activating Token Index: 115

Text #15

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.5596. Min Act: -0.0000

Data Index: 1458812 (Python Code)

Max Activating Token Index: 111

Text #16

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.5713. Min Act: -0.0000

Data Index: 1411473 (Python Code)

Max Activating Token Index: 353

Text #17

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.5696. Min Act: -0.0000

Data Index: 1538282 (Python Code)

Max Activating Token Index: 257

Text #18

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.5576. Min Act: -0.0000

Data Index: 1453496 (Python Code)

Max Activating Token Index: 24

Text #19

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.5381. Min Act: 0.0000

Data Index: 1456977 (Python Code)

Max Activating Token Index: 389