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

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

Neuron 5073 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: 1.7700. Min Range: -1.7700

Max Act: 1.6188. Min Act: -0.0000

Data Index: 1378808 (Python Code)

Max Activating Token Index: 212

Text #1

Max Range: 1.7700. Min Range: -1.7700

Max Act: 1.6877. Min Act: -0.0000

Data Index: 1482831 (Python Code)

Max Activating Token Index: 992

Text #2

Max Range: 1.7700. Min Range: -1.7700

Max Act: 1.6765. Min Act: -0.0000

Data Index: 1638640 (Python Code)

Max Activating Token Index: 263

Text #3

Max Range: 1.7700. Min Range: -1.7700

Max Act: 1.6790. Min Act: -0.0000

Data Index: 1431947 (Python Code)

Max Activating Token Index: 63

Text #4

Max Range: 1.7700. Min Range: -1.7700

Max Act: 1.7700. Min Act: -0.0000

Data Index: 1478275 (Python Code)

Max Activating Token Index: 206

Text #5

Max Range: 1.7700. Min Range: -1.7700

Max Act: 1.5710. Min Act: -0.0000

Data Index: 1375900 (Python Code)

Max Activating Token Index: 76

Text #6

Max Range: 1.7700. Min Range: -1.7700

Max Act: 1.6392. Min Act: -0.0000

Data Index: 1478069 (Python Code)

Max Activating Token Index: 102

Text #7

Max Range: 1.7700. Min Range: -1.7700

Max Act: 1.4559. Min Act: -0.0000

Data Index: 1613398 (Python Code)

Max Activating Token Index: 1017

Text #8

Max Range: 1.7700. Min Range: -1.7700

Max Act: 1.5314. Min Act: -0.0000

Data Index: 1434904 (Python Code)

Max Activating Token Index: 551

Text #9

Max Range: 1.7700. Min Range: -1.7700

Max Act: 1.4197. Min Act: -0.0000

Data Index: 1646514 (Python Code)

Max Activating Token Index: 606

Text #10

Max Range: 1.7700. Min Range: -1.7700

Max Act: 1.4697. Min Act: -0.0000

Data Index: 823995 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 1.7700. Min Range: -1.7700

Max Act: 1.4909. Min Act: -0.0000

Data Index: 1554362 (Python Code)

Max Activating Token Index: 221

Text #12

Max Range: 1.7700. Min Range: -1.7700

Max Act: 1.4626. Min Act: -0.0000

Data Index: 1493101 (Python Code)

Max Activating Token Index: 168

Text #13

Max Range: 1.7700. Min Range: -1.7700

Max Act: 1.5437. Min Act: -0.0000

Data Index: 1513197 (Python Code)

Max Activating Token Index: 155

Text #14

Max Range: 1.7700. Min Range: -1.7700

Max Act: 1.4558. Min Act: -0.0000

Data Index: 1591185 (Python Code)

Max Activating Token Index: 582

Text #15

Max Range: 1.7700. Min Range: -1.7700

Max Act: 1.3617. Min Act: -0.0000

Data Index: 836945 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 1.7700. Min Range: -1.7700

Max Act: 1.4439. Min Act: -0.0000

Data Index: 1440126 (Python Code)

Max Activating Token Index: 519

Text #17

Max Range: 1.7700. Min Range: -1.7700

Max Act: 1.4369. Min Act: -0.0000

Data Index: 1581290 (Python Code)

Max Activating Token Index: 668

Text #18

Max Range: 1.7700. Min Range: -1.7700

Max Act: 1.3466. Min Act: -0.0000

Data Index: 1622440 (Python Code)

Max Activating Token Index: 327

Text #19

Max Range: 1.7700. Min Range: -1.7700

Max Act: 1.4741. Min Act: -0.0000

Data Index: 1532824 (Python Code)

Max Activating Token Index: 102