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

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

Neuron 949 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3911. Min Range: -2.3911

Max Act: 2.3911. Min Act: -0.0000

Data Index: 1534818 (Python Code)

Max Activating Token Index: 548

Text #1

Max Range: 2.3911. Min Range: -2.3911

Max Act: 2.1267. Min Act: -0.0000

Data Index: 1520646 (Python Code)

Max Activating Token Index: 129

Text #2

Max Range: 2.3911. Min Range: -2.3911

Max Act: 2.0923. Min Act: -0.0000

Data Index: 1361385 (Python Code)

Max Activating Token Index: 26

Text #3

Max Range: 2.3911. Min Range: -2.3911

Max Act: 1.9211. Min Act: -0.0000

Data Index: 1564960 (Python Code)

Max Activating Token Index: 884

Text #4

Max Range: 2.3911. Min Range: -2.3911

Max Act: 1.7455. Min Act: -0.0000

Data Index: 1619514 (Python Code)

Max Activating Token Index: 283

Text #5

Max Range: 2.3911. Min Range: -2.3911

Max Act: 1.7517. Min Act: -0.0000

Data Index: 1488359 (Python Code)

Max Activating Token Index: 615

Text #6

Max Range: 2.3911. Min Range: -2.3911

Max Act: 1.7088. Min Act: -0.0000

Data Index: 1360114 (Python Code)

Max Activating Token Index: 325

Text #7

Max Range: 2.3911. Min Range: -2.3911

Max Act: 1.5977. Min Act: -0.0000

Data Index: 1562819 (Python Code)

Max Activating Token Index: 604

Text #8

Max Range: 2.3911. Min Range: -2.3911

Max Act: 1.6032. Min Act: -0.0000

Data Index: 1423497 (Python Code)

Max Activating Token Index: 13

Text #9

Max Range: 2.3911. Min Range: -2.3911

Max Act: 1.5653. Min Act: -0.0000

Data Index: 1644666 (Python Code)

Max Activating Token Index: 389

Text #10

Max Range: 2.3911. Min Range: -2.3911

Max Act: 1.6386. Min Act: -0.0000

Data Index: 1577203 (Python Code)

Max Activating Token Index: 784

Text #11

Max Range: 2.3911. Min Range: -2.3911

Max Act: 1.4127. Min Act: -0.0000

Data Index: 1513118 (Python Code)

Max Activating Token Index: 393

Text #12

Max Range: 2.3911. Min Range: -2.3911

Max Act: 1.3590. Min Act: -0.0000

Data Index: 1536950 (Python Code)

Max Activating Token Index: 44

Text #13

Max Range: 2.3911. Min Range: -2.3911

Max Act: 1.4417. Min Act: -0.0000

Data Index: 1368265 (Python Code)

Max Activating Token Index: 808

Text #14

Max Range: 2.3911. Min Range: -2.3911

Max Act: 1.3429. Min Act: -0.0000

Data Index: 1493870 (Python Code)

Max Activating Token Index: 171

Text #15

Max Range: 2.3911. Min Range: -2.3911

Max Act: 1.4843. Min Act: -0.0000

Data Index: 1590869 (Python Code)

Max Activating Token Index: 83

Text #16

Max Range: 2.3911. Min Range: -2.3911

Max Act: 1.3090. Min Act: -0.0000

Data Index: 1404705 (Python Code)

Max Activating Token Index: 143

Text #17

Max Range: 2.3911. Min Range: -2.3911

Max Act: 1.3862. Min Act: -0.0000

Data Index: 1553092 (Python Code)

Max Activating Token Index: 1005

Text #18

Max Range: 2.3911. Min Range: -2.3911

Max Act: 1.3756. Min Act: -0.0000

Data Index: 1600972 (Python Code)

Max Activating Token Index: 24

Text #19

Max Range: 2.3911. Min Range: -2.3911

Max Act: 1.3631. Min Act: -0.0000

Data Index: 1638980 (Python Code)

Max Activating Token Index: 240