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

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

Neuron 2416 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: 0.0375. Min Range: -0.0375

Max Act: 0.0375. Min Act: -0.0003

Data Index: 704764 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0337. Min Act: -0.0003

Data Index: 1482918 (Python Code)

Max Activating Token Index: 720

Text #2

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0336. Min Act: -0.0003

Data Index: 140914 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0333. Min Act: -0.0003

Data Index: 163384 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0285. Min Act: -0.0003

Data Index: 293777 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0301. Min Act: -0.0003

Data Index: 1508824 (Python Code)

Max Activating Token Index: 917

Text #6

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0289. Min Act: -0.0003

Data Index: 960281 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0284. Min Act: -0.0003

Data Index: 800404 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0296. Min Act: -0.0003

Data Index: 611790 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0285. Min Act: -0.0003

Data Index: 791546 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0264. Min Act: -0.0003

Data Index: 1393379 (Python Code)

Max Activating Token Index: 555

Text #11

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0267. Min Act: -0.0003

Data Index: 63691 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0277. Min Act: -0.0003

Data Index: 696876 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0277. Min Act: -0.0003

Data Index: 1651019 (Python Code)

Max Activating Token Index: 855

Text #14

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0285. Min Act: -0.0003

Data Index: 1369938 (Python Code)

Max Activating Token Index: 668

Text #15

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0260. Min Act: -0.0003

Data Index: 307650 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0304. Min Act: -0.0003

Data Index: 169420 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0284. Min Act: -0.0002

Data Index: 617540 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0283. Min Act: -0.0003

Data Index: 892262 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0275. Min Act: -0.0003

Data Index: 1498615 (Python Code)

Max Activating Token Index: 858