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

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

Neuron 3515 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: 2.4426. Min Range: -2.4426

Max Act: 2.4307. Min Act: -0.0000

Data Index: 1469156 (Python Code)

Max Activating Token Index: 307

Text #1

Max Range: 2.4426. Min Range: -2.4426

Max Act: 2.4426. Min Act: -0.0000

Data Index: 1518568 (Python Code)

Max Activating Token Index: 807

Text #2

Max Range: 2.4426. Min Range: -2.4426

Max Act: 2.2101. Min Act: -0.0000

Data Index: 1647448 (Python Code)

Max Activating Token Index: 953

Text #3

Max Range: 2.4426. Min Range: -2.4426

Max Act: 2.2059. Min Act: -0.0000

Data Index: 1576260 (Python Code)

Max Activating Token Index: 760

Text #4

Max Range: 2.4426. Min Range: -2.4426

Max Act: 2.1568. Min Act: -0.0000

Data Index: 1611292 (Python Code)

Max Activating Token Index: 117

Text #5

Max Range: 2.4426. Min Range: -2.4426

Max Act: 2.2032. Min Act: -0.0000

Data Index: 1433762 (Python Code)

Max Activating Token Index: 283

Text #6

Max Range: 2.4426. Min Range: -2.4426

Max Act: 2.1902. Min Act: -0.0000

Data Index: 1543860 (Python Code)

Max Activating Token Index: 47

Text #7

Max Range: 2.4426. Min Range: -2.4426

Max Act: 2.0221. Min Act: -0.0000

Data Index: 1624496 (Python Code)

Max Activating Token Index: 924

Text #8

Max Range: 2.4426. Min Range: -2.4426

Max Act: 1.9102. Min Act: -0.0000

Data Index: 1573549 (Python Code)

Max Activating Token Index: 101

Text #9

Max Range: 2.4426. Min Range: -2.4426

Max Act: 1.9106. Min Act: -0.0000

Data Index: 1484536 (Python Code)

Max Activating Token Index: 310

Text #10

Max Range: 2.4426. Min Range: -2.4426

Max Act: 1.8975. Min Act: -0.0000

Data Index: 1568894 (Python Code)

Max Activating Token Index: 112

Text #11

Max Range: 2.4426. Min Range: -2.4426

Max Act: 1.9910. Min Act: -0.0000

Data Index: 1616936 (Python Code)

Max Activating Token Index: 940

Text #12

Max Range: 2.4426. Min Range: -2.4426

Max Act: 1.9560. Min Act: -0.0000

Data Index: 1546051 (Python Code)

Max Activating Token Index: 264

Text #13

Max Range: 2.4426. Min Range: -2.4426

Max Act: 1.9411. Min Act: -0.0000

Data Index: 1449014 (Python Code)

Max Activating Token Index: 809

Text #14

Max Range: 2.4426. Min Range: -2.4426

Max Act: 1.8125. Min Act: -0.0000

Data Index: 1480151 (Python Code)

Max Activating Token Index: 264

Text #15

Max Range: 2.4426. Min Range: -2.4426

Max Act: 1.8867. Min Act: -0.0000

Data Index: 1564948 (Python Code)

Max Activating Token Index: 314

Text #16

Max Range: 2.4426. Min Range: -2.4426

Max Act: 2.1016. Min Act: -0.0000

Data Index: 1587420 (Python Code)

Max Activating Token Index: 782

Text #17

Max Range: 2.4426. Min Range: -2.4426

Max Act: 1.8818. Min Act: -0.0000

Data Index: 1432234 (Python Code)

Max Activating Token Index: 931

Text #18

Max Range: 2.4426. Min Range: -2.4426

Max Act: 1.6589. Min Act: -0.0000

Data Index: 1601286 (Python Code)

Max Activating Token Index: 306

Text #19

Max Range: 2.4426. Min Range: -2.4426

Max Act: 1.8505. Min Act: -0.0000

Data Index: 1469294 (Python Code)

Max Activating Token Index: 515