Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 644 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0475. Min Act: -0.0002

Data Index: 1492796 (Python Code)

Max Activating Token Index: 5

Text #1

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0475. Min Act: -0.0002

Data Index: 1385101 (Python Code)

Max Activating Token Index: 5

Text #2

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0475. Min Act: -0.0002

Data Index: 1362502 (Python Code)

Max Activating Token Index: 5

Text #3

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0382. Min Act: -0.0002

Data Index: 1405540 (Python Code)

Max Activating Token Index: 317

Text #4

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0338. Min Act: -0.0002

Data Index: 1409203 (Python Code)

Max Activating Token Index: 266

Text #5

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0368. Min Act: -0.0002

Data Index: 685999 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0378. Min Act: -0.0002

Data Index: 1410504 (Python Code)

Max Activating Token Index: 892

Text #7

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0356. Min Act: -0.0002

Data Index: 1426860 (Python Code)

Max Activating Token Index: 608

Text #8

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0383. Min Act: -0.0002

Data Index: 1466283 (Python Code)

Max Activating Token Index: 138

Text #9

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0369. Min Act: -0.0002

Data Index: 886201 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0368. Min Act: -0.0002

Data Index: 1638054 (Python Code)

Max Activating Token Index: 116

Text #11

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0361. Min Act: -0.0002

Data Index: 446155 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0364. Min Act: -0.0002

Data Index: 1508214 (Python Code)

Max Activating Token Index: 136

Text #13

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0377. Min Act: -0.0002

Data Index: 375986 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0383. Min Act: -0.0002

Data Index: 1468020 (Python Code)

Max Activating Token Index: 1010

Text #15

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0371. Min Act: -0.0002

Data Index: 313227 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0373. Min Act: -0.0002

Data Index: 1638737 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0365. Min Act: -0.0002

Data Index: 1560993 (Python Code)

Max Activating Token Index: 368

Text #18

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1510809 (Python Code)

Max Activating Token Index: 192

Text #19

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0340. Min Act: -0.0002

Data Index: 557364 (C4 (Web Text))

Max Activating Token Index: 727