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

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

Neuron 4024 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8519. Min Range: -2.8519

Max Act: 2.5532. Min Act: -0.0000

Data Index: 1439009 (Python Code)

Max Activating Token Index: 574

Text #1

Max Range: 2.8519. Min Range: -2.8519

Max Act: 2.6611. Min Act: -0.0000

Data Index: 1650997 (Python Code)

Max Activating Token Index: 480

Text #2

Max Range: 2.8519. Min Range: -2.8519

Max Act: 2.4647. Min Act: -0.0000

Data Index: 1608016 (Python Code)

Max Activating Token Index: 260

Text #3

Max Range: 2.8519. Min Range: -2.8519

Max Act: 2.7233. Min Act: -0.0000

Data Index: 1430230 (Python Code)

Max Activating Token Index: 579

Text #4

Max Range: 2.8519. Min Range: -2.8519

Max Act: 2.4349. Min Act: -0.0000

Data Index: 1374256 (Python Code)

Max Activating Token Index: 688

Text #5

Max Range: 2.8519. Min Range: -2.8519

Max Act: 2.6789. Min Act: -0.0000

Data Index: 1415140 (Python Code)

Max Activating Token Index: 419

Text #6

Max Range: 2.8519. Min Range: -2.8519

Max Act: 2.6798. Min Act: -0.0000

Data Index: 1478007 (Python Code)

Max Activating Token Index: 893

Text #7

Max Range: 2.8519. Min Range: -2.8519

Max Act: 2.3304. Min Act: -0.0000

Data Index: 1404728 (Python Code)

Max Activating Token Index: 195

Text #8

Max Range: 2.8519. Min Range: -2.8519

Max Act: 2.8336. Min Act: -0.0000

Data Index: 1577886 (Python Code)

Max Activating Token Index: 102

Text #9

Max Range: 2.8519. Min Range: -2.8519

Max Act: 2.5656. Min Act: -0.0000

Data Index: 1412538 (Python Code)

Max Activating Token Index: 508

Text #10

Max Range: 2.8519. Min Range: -2.8519

Max Act: 2.5317. Min Act: -0.0000

Data Index: 1541221 (Python Code)

Max Activating Token Index: 757

Text #11

Max Range: 2.8519. Min Range: -2.8519

Max Act: 2.4785. Min Act: -0.0000

Data Index: 1569495 (Python Code)

Max Activating Token Index: 110

Text #12

Max Range: 2.8519. Min Range: -2.8519

Max Act: 2.2259. Min Act: -0.0001

Data Index: 1464032 (Python Code)

Max Activating Token Index: 1020

Text #13

Max Range: 2.8519. Min Range: -2.8519

Max Act: 2.2370. Min Act: -0.0000

Data Index: 1406762 (Python Code)

Max Activating Token Index: 324

Text #14

Max Range: 2.8519. Min Range: -2.8519

Max Act: 2.8519. Min Act: -0.0000

Data Index: 1479690 (Python Code)

Max Activating Token Index: 787

Text #15

Max Range: 2.8519. Min Range: -2.8519

Max Act: 2.4206. Min Act: -0.0000

Data Index: 1571695 (Python Code)

Max Activating Token Index: 891

Text #16

Max Range: 2.8519. Min Range: -2.8519

Max Act: 2.3125. Min Act: -0.0000

Data Index: 1365248 (Python Code)

Max Activating Token Index: 43

Text #17

Max Range: 2.8519. Min Range: -2.8519

Max Act: 1.8934. Min Act: -0.0000

Data Index: 1515163 (Python Code)

Max Activating Token Index: 218

Text #18

Max Range: 2.8519. Min Range: -2.8519

Max Act: 2.2997. Min Act: -0.0000

Data Index: 1364322 (Python Code)

Max Activating Token Index: 557

Text #19

Max Range: 2.8519. Min Range: -2.8519

Max Act: 2.1343. Min Act: -0.0000

Data Index: 1555395 (Python Code)

Max Activating Token Index: 249