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

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

Neuron 1284 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.6289. Min Range: -1.6289

Max Act: 1.6289. Min Act: -0.0002

Data Index: 1415305 (Python Code)

Max Activating Token Index: 361

Text #1

Max Range: 1.6289. Min Range: -1.6289

Max Act: 1.6116. Min Act: -0.0002

Data Index: 1587193 (Python Code)

Max Activating Token Index: 17

Text #2

Max Range: 1.6289. Min Range: -1.6289

Max Act: 1.5685. Min Act: -0.0002

Data Index: 1392677 (Python Code)

Max Activating Token Index: 15

Text #3

Max Range: 1.6289. Min Range: -1.6289

Max Act: 1.4713. Min Act: -0.0002

Data Index: 799577 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 1.6289. Min Range: -1.6289

Max Act: 1.4488. Min Act: -0.0002

Data Index: 1401125 (Python Code)

Max Activating Token Index: 43

Text #5

Max Range: 1.6289. Min Range: -1.6289

Max Act: 1.4023. Min Act: -0.0002

Data Index: 533363 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 1.6289. Min Range: -1.6289

Max Act: 1.3609. Min Act: -0.0002

Data Index: 1652318 (Python Code)

Max Activating Token Index: 29

Text #7

Max Range: 1.6289. Min Range: -1.6289

Max Act: 1.3700. Min Act: -0.0002

Data Index: 1501148 (Python Code)

Max Activating Token Index: 30

Text #8

Max Range: 1.6289. Min Range: -1.6289

Max Act: 1.3975. Min Act: -0.0002

Data Index: 1610132 (Python Code)

Max Activating Token Index: 704

Text #9

Max Range: 1.6289. Min Range: -1.6289

Max Act: 1.3544. Min Act: -0.0002

Data Index: 1431241 (Python Code)

Max Activating Token Index: 270

Text #10

Max Range: 1.6289. Min Range: -1.6289

Max Act: 1.3586. Min Act: -0.0002

Data Index: 1540157 (Python Code)

Max Activating Token Index: 19

Text #11

Max Range: 1.6289. Min Range: -1.6289

Max Act: 1.3417. Min Act: -0.0002

Data Index: 1394846 (Python Code)

Max Activating Token Index: 430

Text #12

Max Range: 1.6289. Min Range: -1.6289

Max Act: 1.3551. Min Act: -0.0002

Data Index: 1427409 (Python Code)

Max Activating Token Index: 234

Text #13

Max Range: 1.6289. Min Range: -1.6289

Max Act: 1.3346. Min Act: -0.0002

Data Index: 1403621 (Python Code)

Max Activating Token Index: 302

Text #14

Max Range: 1.6289. Min Range: -1.6289

Max Act: 1.3276. Min Act: -0.0002

Data Index: 1587152 (Python Code)

Max Activating Token Index: 11

Text #15

Max Range: 1.6289. Min Range: -1.6289

Max Act: 1.3360. Min Act: -0.0002

Data Index: 1620773 (Python Code)

Max Activating Token Index: 406

Text #16

Max Range: 1.6289. Min Range: -1.6289

Max Act: 1.3284. Min Act: -0.0002

Data Index: 1542282 (Python Code)

Max Activating Token Index: 37

Text #17

Max Range: 1.6289. Min Range: -1.6289

Max Act: 1.3305. Min Act: -0.0002

Data Index: 1529700 (Python Code)

Max Activating Token Index: 590

Text #18

Max Range: 1.6289. Min Range: -1.6289

Max Act: 1.2978. Min Act: -0.0002

Data Index: 1583373 (Python Code)

Max Activating Token Index: 38

Text #19

Max Range: 1.6289. Min Range: -1.6289

Max Act: 1.2964. Min Act: -0.0002

Data Index: 1468660 (Python Code)

Max Activating Token Index: 38