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

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

Neuron 2906 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.9010. Min Act: -0.0000

Data Index: 1446710 (Python Code)

Max Activating Token Index: 58

Text #1

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.7102. Min Act: -0.0000

Data Index: 1404670 (Python Code)

Max Activating Token Index: 573

Text #2

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.5030. Min Act: -0.0000

Data Index: 1384335 (Python Code)

Max Activating Token Index: 440

Text #3

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.5404. Min Act: -0.0000

Data Index: 1488530 (Python Code)

Max Activating Token Index: 706

Text #4

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.3433. Min Act: -0.0000

Data Index: 1416089 (Python Code)

Max Activating Token Index: 727

Text #5

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.4360. Min Act: -0.0000

Data Index: 1535399 (Python Code)

Max Activating Token Index: 851

Text #6

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.3256. Min Act: -0.0000

Data Index: 1352230 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.1308. Min Act: -0.0000

Data Index: 1105712 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.1983. Min Act: -0.0000

Data Index: 1158097 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.1181. Min Act: -0.0000

Data Index: 343675 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.1513. Min Act: -0.0000

Data Index: 1601134 (Python Code)

Max Activating Token Index: 836

Text #11

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.1445. Min Act: -0.0000

Data Index: 28056 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.0731. Min Act: -0.0000

Data Index: 1452669 (Python Code)

Max Activating Token Index: 427

Text #13

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.1391. Min Act: -0.0000

Data Index: 1395105 (Python Code)

Max Activating Token Index: 1021

Text #14

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.0822. Min Act: -0.0000

Data Index: 1461690 (Python Code)

Max Activating Token Index: 357

Text #15

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.1861. Min Act: -0.0000

Data Index: 820484 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.0999. Min Act: -0.0000

Data Index: 1396524 (Python Code)

Max Activating Token Index: 241

Text #17

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.1038. Min Act: -0.0000

Data Index: 1555257 (Python Code)

Max Activating Token Index: 899

Text #18

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.0985. Min Act: -0.0000

Data Index: 1171069 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.0673. Min Act: -0.0000

Data Index: 302094 (C4 (Web Text))

Max Activating Token Index: 909