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

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

Neuron 3183 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.6329. Min Act: 0.0000

Data Index: 1393624 (Python Code)

Max Activating Token Index: 601

Text #1

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.6616. Min Act: 0.0000

Data Index: 1443296 (Python Code)

Max Activating Token Index: 328

Text #2

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.5753. Min Act: -0.0000

Data Index: 1046646 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.4707. Min Act: -0.0000

Data Index: 220856 (C4 (Web Text))

Max Activating Token Index: 733

Text #4

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.4829. Min Act: -0.0000

Data Index: 1648950 (Python Code)

Max Activating Token Index: 232

Text #5

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.4623. Min Act: -0.0000

Data Index: 1488314 (Python Code)

Max Activating Token Index: 186

Text #6

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.4408. Min Act: -0.0000

Data Index: 1508516 (Python Code)

Max Activating Token Index: 156

Text #7

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.4914. Min Act: -0.0000

Data Index: 1434166 (Python Code)

Max Activating Token Index: 310

Text #8

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.4496. Min Act: 0.0000

Data Index: 1566504 (Python Code)

Max Activating Token Index: 404

Text #9

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.4291. Min Act: 0.0000

Data Index: 1609436 (Python Code)

Max Activating Token Index: 521

Text #10

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.4590. Min Act: -0.0000

Data Index: 1631882 (Python Code)

Max Activating Token Index: 691

Text #11

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.4256. Min Act: -0.0000

Data Index: 1375060 (Python Code)

Max Activating Token Index: 986

Text #12

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.4246. Min Act: 0.0000

Data Index: 1568599 (Python Code)

Max Activating Token Index: 1016

Text #13

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.4045. Min Act: -0.0000

Data Index: 601948 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.4651. Min Act: -0.0000

Data Index: 408198 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.4015. Min Act: 0.0000

Data Index: 191538 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.4090. Min Act: -0.0000

Data Index: 1511468 (Python Code)

Max Activating Token Index: 843

Text #17

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.3845. Min Act: -0.0000

Data Index: 1380552 (Python Code)

Max Activating Token Index: 916

Text #18

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.3850. Min Act: -0.0000

Data Index: 1410097 (Python Code)

Max Activating Token Index: 149

Text #19

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.3908. Min Act: 0.0000

Data Index: 1543875 (Python Code)

Max Activating Token Index: 883