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

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

Neuron 3655 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: 0.0397. Min Range: -0.0397

Max Act: 0.0397. Min Act: -0.0002

Data Index: 1500212 (Python Code)

Max Activating Token Index: 835

Text #1

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0378. Min Act: -0.0002

Data Index: 1622027 (Python Code)

Max Activating Token Index: 513

Text #2

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0360. Min Act: -0.0002

Data Index: 1401010 (Python Code)

Max Activating Token Index: 626

Text #3

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0358. Min Act: -0.0002

Data Index: 1530761 (Python Code)

Max Activating Token Index: 652

Text #4

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1381869 (Python Code)

Max Activating Token Index: 736

Text #5

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0353. Min Act: -0.0002

Data Index: 1389907 (Python Code)

Max Activating Token Index: 380

Text #6

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0352. Min Act: -0.0002

Data Index: 1420712 (Python Code)

Max Activating Token Index: 843

Text #7

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0354. Min Act: -0.0002

Data Index: 1371323 (Python Code)

Max Activating Token Index: 48

Text #8

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0351. Min Act: -0.0002

Data Index: 1365776 (Python Code)

Max Activating Token Index: 162

Text #9

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0343. Min Act: -0.0002

Data Index: 1582805 (Python Code)

Max Activating Token Index: 245

Text #10

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0344. Min Act: -0.0002

Data Index: 1641199 (Python Code)

Max Activating Token Index: 56

Text #11

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0346. Min Act: -0.0002

Data Index: 1603842 (Python Code)

Max Activating Token Index: 212

Text #12

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0341. Min Act: -0.0002

Data Index: 1451100 (Python Code)

Max Activating Token Index: 165

Text #13

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0346. Min Act: -0.0002

Data Index: 1517896 (Python Code)

Max Activating Token Index: 714

Text #14

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1602747 (Python Code)

Max Activating Token Index: 343

Text #15

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1392442 (Python Code)

Max Activating Token Index: 837

Text #16

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0334. Min Act: -0.0002

Data Index: 1637367 (Python Code)

Max Activating Token Index: 310

Text #17

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1546739 (Python Code)

Max Activating Token Index: 268

Text #18

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0328. Min Act: -0.0002

Data Index: 1652553 (Python Code)

Max Activating Token Index: 380

Text #19

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1471085 (Python Code)

Max Activating Token Index: 973