Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3777 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9208. Min Range: -1.9208

Max Act: 1.9096. Min Act: -0.0002

Data Index: 1531712 (Python Code)

Max Activating Token Index: 240

Text #1

Max Range: 1.9208. Min Range: -1.9208

Max Act: 1.9002. Min Act: -0.0002

Data Index: 1525701 (Python Code)

Max Activating Token Index: 354

Text #2

Max Range: 1.9208. Min Range: -1.9208

Max Act: 1.7313. Min Act: -0.0002

Data Index: 1428318 (Python Code)

Max Activating Token Index: 950

Text #3

Max Range: 1.9208. Min Range: -1.9208

Max Act: 1.8153. Min Act: -0.0002

Data Index: 1491234 (Python Code)

Max Activating Token Index: 956

Text #4

Max Range: 1.9208. Min Range: -1.9208

Max Act: 1.7572. Min Act: -0.0002

Data Index: 1633227 (Python Code)

Max Activating Token Index: 908

Text #5

Max Range: 1.9208. Min Range: -1.9208

Max Act: 1.7784. Min Act: -0.0002

Data Index: 1380933 (Python Code)

Max Activating Token Index: 617

Text #6

Max Range: 1.9208. Min Range: -1.9208

Max Act: 1.8394. Min Act: -0.0002

Data Index: 1561387 (Python Code)

Max Activating Token Index: 317

Text #7

Max Range: 1.9208. Min Range: -1.9208

Max Act: 1.7209. Min Act: -0.0002

Data Index: 1476789 (Python Code)

Max Activating Token Index: 304

Text #8

Max Range: 1.9208. Min Range: -1.9208

Max Act: 1.7563. Min Act: -0.0002

Data Index: 1418905 (Python Code)

Max Activating Token Index: 923

Text #9

Max Range: 1.9208. Min Range: -1.9208

Max Act: 1.5918. Min Act: -0.0002

Data Index: 1580067 (Python Code)

Max Activating Token Index: 807

Text #10

Max Range: 1.9208. Min Range: -1.9208

Max Act: 1.8029. Min Act: -0.0002

Data Index: 1625608 (Python Code)

Max Activating Token Index: 664

Text #11

Max Range: 1.9208. Min Range: -1.9208

Max Act: 1.7842. Min Act: -0.0002

Data Index: 1530355 (Python Code)

Max Activating Token Index: 881

Text #12

Max Range: 1.9208. Min Range: -1.9208

Max Act: 1.6289. Min Act: -0.0002

Data Index: 1385684 (Python Code)

Max Activating Token Index: 832

Text #13

Max Range: 1.9208. Min Range: -1.9208

Max Act: 1.7971. Min Act: -0.0002

Data Index: 1599983 (Python Code)

Max Activating Token Index: 584

Text #14

Max Range: 1.9208. Min Range: -1.9208

Max Act: 1.7358. Min Act: -0.0002

Data Index: 1421988 (Python Code)

Max Activating Token Index: 983

Text #15

Max Range: 1.9208. Min Range: -1.9208

Max Act: 1.6757. Min Act: -0.0002

Data Index: 1529791 (Python Code)

Max Activating Token Index: 798

Text #16

Max Range: 1.9208. Min Range: -1.9208

Max Act: 1.8246. Min Act: -0.0002

Data Index: 1500536 (Python Code)

Max Activating Token Index: 412

Text #17

Max Range: 1.9208. Min Range: -1.9208

Max Act: 1.9208. Min Act: -0.0002

Data Index: 1564859 (Python Code)

Max Activating Token Index: 980

Text #18

Max Range: 1.9208. Min Range: -1.9208

Max Act: 1.7202. Min Act: -0.0002

Data Index: 1534967 (Python Code)

Max Activating Token Index: 1022

Text #19

Max Range: 1.9208. Min Range: -1.9208

Max Act: 1.6739. Min Act: -0.0002

Data Index: 1512404 (Python Code)

Max Activating Token Index: 203