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

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

Neuron 4604 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8217. Min Range: -3.8217

Max Act: 3.8217. Min Act: -0.0000

Data Index: 1609086 (Python Code)

Max Activating Token Index: 811

Text #1

Max Range: 3.8217. Min Range: -3.8217

Max Act: 2.9778. Min Act: -0.0000

Data Index: 1581840 (Python Code)

Max Activating Token Index: 967

Text #2

Max Range: 3.8217. Min Range: -3.8217

Max Act: 2.9847. Min Act: -0.0000

Data Index: 1462999 (Python Code)

Max Activating Token Index: 92

Text #3

Max Range: 3.8217. Min Range: -3.8217

Max Act: 2.7973. Min Act: -0.0000

Data Index: 1513762 (Python Code)

Max Activating Token Index: 871

Text #4

Max Range: 3.8217. Min Range: -3.8217

Max Act: 2.5979. Min Act: -0.0000

Data Index: 1376260 (Python Code)

Max Activating Token Index: 310

Text #5

Max Range: 3.8217. Min Range: -3.8217

Max Act: 2.5702. Min Act: -0.0000

Data Index: 1604853 (Python Code)

Max Activating Token Index: 897

Text #6

Max Range: 3.8217. Min Range: -3.8217

Max Act: 2.4908. Min Act: -0.0000

Data Index: 1519134 (Python Code)

Max Activating Token Index: 1011

Text #7

Max Range: 3.8217. Min Range: -3.8217

Max Act: 2.4283. Min Act: -0.0000

Data Index: 1214773 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 3.8217. Min Range: -3.8217

Max Act: 2.1336. Min Act: -0.0000

Data Index: 1421808 (Python Code)

Max Activating Token Index: 990

Text #9

Max Range: 3.8217. Min Range: -3.8217

Max Act: 2.3673. Min Act: -0.0000

Data Index: 1394771 (Python Code)

Max Activating Token Index: 410

Text #10

Max Range: 3.8217. Min Range: -3.8217

Max Act: 2.6182. Min Act: -0.0000

Data Index: 1626604 (Python Code)

Max Activating Token Index: 536

Text #11

Max Range: 3.8217. Min Range: -3.8217

Max Act: 2.2923. Min Act: -0.0000

Data Index: 1454190 (Python Code)

Max Activating Token Index: 249

Text #12

Max Range: 3.8217. Min Range: -3.8217

Max Act: 2.2677. Min Act: -0.0000

Data Index: 1530858 (Python Code)

Max Activating Token Index: 280

Text #13

Max Range: 3.8217. Min Range: -3.8217

Max Act: 1.9197. Min Act: -0.0000

Data Index: 1392005 (Python Code)

Max Activating Token Index: 364

Text #14

Max Range: 3.8217. Min Range: -3.8217

Max Act: 2.2627. Min Act: -0.0000

Data Index: 1565873 (Python Code)

Max Activating Token Index: 78

Text #15

Max Range: 3.8217. Min Range: -3.8217

Max Act: 2.3239. Min Act: -0.0000

Data Index: 1480853 (Python Code)

Max Activating Token Index: 64

Text #16

Max Range: 3.8217. Min Range: -3.8217

Max Act: 2.2515. Min Act: -0.0000

Data Index: 1603106 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 3.8217. Min Range: -3.8217

Max Act: 2.2282. Min Act: -0.0000

Data Index: 1486911 (Python Code)

Max Activating Token Index: 1008

Text #18

Max Range: 3.8217. Min Range: -3.8217

Max Act: 2.1902. Min Act: -0.0000

Data Index: 1437974 (Python Code)

Max Activating Token Index: 134

Text #19

Max Range: 3.8217. Min Range: -3.8217

Max Act: 2.2607. Min Act: -0.0000

Data Index: 1482340 (Python Code)

Max Activating Token Index: 78