Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2087 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.6264. Min Act: -0.0003

Data Index: 617161 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.3692. Min Act: -0.0003

Data Index: 999193 (C4 (Web Text))

Max Activating Token Index: 591

Text #2

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.4292. Min Act: -0.0003

Data Index: 1482866 (Python Code)

Max Activating Token Index: 796

Text #3

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.4181. Min Act: -0.0003

Data Index: 1380542 (Python Code)

Max Activating Token Index: 823

Text #4

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.4237. Min Act: -0.0003

Data Index: 766621 (C4 (Web Text))

Max Activating Token Index: 337

Text #5

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.4064. Min Act: -0.0003

Data Index: 1515649 (Python Code)

Max Activating Token Index: 585

Text #6

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.4196. Min Act: -0.0003

Data Index: 1642926 (Python Code)

Max Activating Token Index: 700

Text #7

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.4413. Min Act: -0.0003

Data Index: 1469929 (Python Code)

Max Activating Token Index: 32

Text #8

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.4065. Min Act: -0.0003

Data Index: 1623207 (Python Code)

Max Activating Token Index: 652

Text #9

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.4385. Min Act: -0.0003

Data Index: 921613 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.4353. Min Act: -0.0003

Data Index: 1516210 (Python Code)

Max Activating Token Index: 109

Text #11

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.4375. Min Act: -0.0003

Data Index: 1534946 (Python Code)

Max Activating Token Index: 489

Text #12

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.4043. Min Act: -0.0003

Data Index: 1497419 (Python Code)

Max Activating Token Index: 780

Text #13

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.3865. Min Act: -0.0003

Data Index: 1584079 (Python Code)

Max Activating Token Index: 175

Text #14

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.4410. Min Act: -0.0003

Data Index: 1496127 (Python Code)

Max Activating Token Index: 667

Text #15

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.4005. Min Act: -0.0003

Data Index: 1333369 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.4112. Min Act: -0.0003

Data Index: 1073251 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.4256. Min Act: -0.0003

Data Index: 1497788 (Python Code)

Max Activating Token Index: 912

Text #18

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.4390. Min Act: -0.0003

Data Index: 1550801 (Python Code)

Max Activating Token Index: 702

Text #19

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.3954. Min Act: -0.0003

Data Index: 704170 (C4 (Web Text))

Max Activating Token Index: 371