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

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

Neuron 4698 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.8740. Min Act: -0.0000

Data Index: 1485335 (Python Code)

Max Activating Token Index: 386

Text #1

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.8288. Min Act: -0.0000

Data Index: 1623650 (Python Code)

Max Activating Token Index: 589

Text #2

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.7099. Min Act: -0.0000

Data Index: 1442810 (Python Code)

Max Activating Token Index: 699

Text #3

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.7176. Min Act: -0.0000

Data Index: 1472109 (Python Code)

Max Activating Token Index: 1014

Text #4

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.7006. Min Act: -0.0000

Data Index: 1418222 (Python Code)

Max Activating Token Index: 451

Text #5

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.6490. Min Act: -0.0000

Data Index: 1428263 (Python Code)

Max Activating Token Index: 395

Text #6

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.7331. Min Act: -0.0000

Data Index: 1560455 (Python Code)

Max Activating Token Index: 640

Text #7

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.6989. Min Act: -0.0000

Data Index: 1583913 (Python Code)

Max Activating Token Index: 364

Text #8

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.6635. Min Act: -0.0000

Data Index: 1587508 (Python Code)

Max Activating Token Index: 401

Text #9

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.6390. Min Act: -0.0000

Data Index: 1620621 (Python Code)

Max Activating Token Index: 716

Text #10

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.6377. Min Act: -0.0000

Data Index: 1565711 (Python Code)

Max Activating Token Index: 40

Text #11

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.5108. Min Act: -0.0000

Data Index: 1404802 (Python Code)

Max Activating Token Index: 781

Text #12

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.6804. Min Act: -0.0000

Data Index: 1424853 (Python Code)

Max Activating Token Index: 913

Text #13

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.6448. Min Act: -0.0000

Data Index: 1370642 (Python Code)

Max Activating Token Index: 610

Text #14

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.5576. Min Act: -0.0000

Data Index: 1541826 (Python Code)

Max Activating Token Index: 712

Text #15

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.5484. Min Act: -0.0000

Data Index: 935149 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.5315. Min Act: -0.0000

Data Index: 1583687 (Python Code)

Max Activating Token Index: 148

Text #17

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.5930. Min Act: -0.0000

Data Index: 1432663 (Python Code)

Max Activating Token Index: 541

Text #18

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.5123. Min Act: -0.0000

Data Index: 1655486 (Python Code)

Max Activating Token Index: 382

Text #19

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.5808. Min Act: -0.0000

Data Index: 1531672 (Python Code)

Max Activating Token Index: 158