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

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

Neuron 3669 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.4770. Min Act: -0.0000

Data Index: 1543477 (Python Code)

Max Activating Token Index: 525

Text #1

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.3426. Min Act: -0.0000

Data Index: 1197299 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.2822. Min Act: -0.0000

Data Index: 1361181 (Python Code)

Max Activating Token Index: 967

Text #3

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.2686. Min Act: -0.0000

Data Index: 430404 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.1229. Min Act: -0.0000

Data Index: 232328 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.0607. Min Act: -0.0000

Data Index: 1644554 (Python Code)

Max Activating Token Index: 601

Text #6

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.1000. Min Act: -0.0000

Data Index: 1583839 (Python Code)

Max Activating Token Index: 661

Text #7

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.1164. Min Act: -0.0000

Data Index: 1539941 (Python Code)

Max Activating Token Index: 310

Text #8

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.0992. Min Act: -0.0000

Data Index: 591523 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.1108. Min Act: -0.0000

Data Index: 1483289 (Python Code)

Max Activating Token Index: 979

Text #10

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.0569. Min Act: -0.0000

Data Index: 1453094 (Python Code)

Max Activating Token Index: 746

Text #11

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.0565. Min Act: -0.0000

Data Index: 1108262 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.0269. Min Act: -0.0000

Data Index: 1650906 (Python Code)

Max Activating Token Index: 660

Text #13

Max Range: 1.4770. Min Range: -1.4770

Max Act: 0.9365. Min Act: -0.0000

Data Index: 643934 (C4 (Web Text))

Max Activating Token Index: 587

Text #14

Max Range: 1.4770. Min Range: -1.4770

Max Act: 0.9309. Min Act: -0.0000

Data Index: 1565553 (Python Code)

Max Activating Token Index: 346

Text #15

Max Range: 1.4770. Min Range: -1.4770

Max Act: 0.9379. Min Act: -0.0000

Data Index: 156060 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 1.4770. Min Range: -1.4770

Max Act: 0.9005. Min Act: -0.0000

Data Index: 1639592 (Python Code)

Max Activating Token Index: 679

Text #17

Max Range: 1.4770. Min Range: -1.4770

Max Act: 0.9218. Min Act: -0.0000

Data Index: 570756 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 1.4770. Min Range: -1.4770

Max Act: 0.9131. Min Act: -0.0000

Data Index: 769784 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 1.4770. Min Range: -1.4770

Max Act: 0.9387. Min Act: -0.0000

Data Index: 1476400 (Python Code)

Max Activating Token Index: 33