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

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

Neuron 2046 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6288. Min Range: -1.6288

Max Act: 1.6288. Min Act: -0.0000

Data Index: 204567 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 1.6288. Min Range: -1.6288

Max Act: 1.2107. Min Act: -0.0000

Data Index: 1533584 (Python Code)

Max Activating Token Index: 582

Text #2

Max Range: 1.6288. Min Range: -1.6288

Max Act: 1.0369. Min Act: -0.0000

Data Index: 1587118 (Python Code)

Max Activating Token Index: 842

Text #3

Max Range: 1.6288. Min Range: -1.6288

Max Act: 1.0320. Min Act: -0.0000

Data Index: 1520577 (Python Code)

Max Activating Token Index: 637

Text #4

Max Range: 1.6288. Min Range: -1.6288

Max Act: 0.9616. Min Act: -0.0000

Data Index: 34434 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 1.6288. Min Range: -1.6288

Max Act: 0.9121. Min Act: -0.0000

Data Index: 834294 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 1.6288. Min Range: -1.6288

Max Act: 0.8724. Min Act: -0.0000

Data Index: 162797 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 1.6288. Min Range: -1.6288

Max Act: 0.8611. Min Act: -0.0000

Data Index: 1395689 (Python Code)

Max Activating Token Index: 795

Text #8

Max Range: 1.6288. Min Range: -1.6288

Max Act: 0.8553. Min Act: -0.0000

Data Index: 1399576 (Python Code)

Max Activating Token Index: 501

Text #9

Max Range: 1.6288. Min Range: -1.6288

Max Act: 0.8508. Min Act: -0.0000

Data Index: 1535942 (Python Code)

Max Activating Token Index: 982

Text #10

Max Range: 1.6288. Min Range: -1.6288

Max Act: 0.7670. Min Act: -0.0000

Data Index: 1035194 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 1.6288. Min Range: -1.6288

Max Act: 0.7974. Min Act: -0.0000

Data Index: 1419803 (Python Code)

Max Activating Token Index: 944

Text #12

Max Range: 1.6288. Min Range: -1.6288

Max Act: 0.7566. Min Act: -0.0000

Data Index: 884443 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 1.6288. Min Range: -1.6288

Max Act: 0.6896. Min Act: -0.0000

Data Index: 890556 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 1.6288. Min Range: -1.6288

Max Act: 0.7879. Min Act: -0.0000

Data Index: 238473 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 1.6288. Min Range: -1.6288

Max Act: 0.8233. Min Act: -0.0000

Data Index: 143593 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 1.6288. Min Range: -1.6288

Max Act: 0.7547. Min Act: -0.0000

Data Index: 1095211 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 1.6288. Min Range: -1.6288

Max Act: 0.7350. Min Act: -0.0000

Data Index: 1636131 (Python Code)

Max Activating Token Index: 45

Text #18

Max Range: 1.6288. Min Range: -1.6288

Max Act: 0.6896. Min Act: -0.0000

Data Index: 1376036 (Python Code)

Max Activating Token Index: 62

Text #19

Max Range: 1.6288. Min Range: -1.6288

Max Act: 0.7546. Min Act: -0.0000

Data Index: 897336 (C4 (Web Text))

Max Activating Token Index: 242