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

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

Neuron 3015 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.7119. Min Act: -0.0000

Data Index: 1537008 (Python Code)

Max Activating Token Index: 904

Text #1

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.5917. Min Act: -0.0000

Data Index: 1248538 (C4 (Web Text))

Max Activating Token Index: 923

Text #2

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.5129. Min Act: -0.0000

Data Index: 1372059 (Python Code)

Max Activating Token Index: 232

Text #3

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.5301. Min Act: -0.0000

Data Index: 1401958 (Python Code)

Max Activating Token Index: 612

Text #4

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.5055. Min Act: -0.0000

Data Index: 1605082 (Python Code)

Max Activating Token Index: 560

Text #5

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.5015. Min Act: -0.0000

Data Index: 1617334 (Python Code)

Max Activating Token Index: 393

Text #6

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.4704. Min Act: -0.0000

Data Index: 1496261 (Python Code)

Max Activating Token Index: 945

Text #7

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.4673. Min Act: -0.0000

Data Index: 1380189 (Python Code)

Max Activating Token Index: 997

Text #8

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.4502. Min Act: -0.0000

Data Index: 1432292 (Python Code)

Max Activating Token Index: 893

Text #9

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.4599. Min Act: -0.0000

Data Index: 1376493 (Python Code)

Max Activating Token Index: 541

Text #10

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.4513. Min Act: -0.0000

Data Index: 1396792 (Python Code)

Max Activating Token Index: 238

Text #11

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.4502. Min Act: -0.0000

Data Index: 1584447 (Python Code)

Max Activating Token Index: 87

Text #12

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.4208. Min Act: -0.0000

Data Index: 1654793 (Python Code)

Max Activating Token Index: 168

Text #13

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.4695. Min Act: -0.0000

Data Index: 1391586 (Python Code)

Max Activating Token Index: 822

Text #14

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.4277. Min Act: -0.0000

Data Index: 747566 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.4271. Min Act: -0.0000

Data Index: 1542619 (Python Code)

Max Activating Token Index: 504

Text #16

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.4367. Min Act: -0.0000

Data Index: 1656521 (Python Code)

Max Activating Token Index: 781

Text #17

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.4230. Min Act: -0.0000

Data Index: 837831 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.4137. Min Act: -0.0000

Data Index: 1639523 (Python Code)

Max Activating Token Index: 12

Text #19

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.3983. Min Act: -0.0000

Data Index: 1522650 (Python Code)

Max Activating Token Index: 139