Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1321 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1999. Min Act: -0.0001

Data Index: 1204497 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1620. Min Act: -0.0001

Data Index: 215896 (C4 (Web Text))

Max Activating Token Index: 288

Text #2

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1660. Min Act: -0.0001

Data Index: 1547117 (Python Code)

Max Activating Token Index: 998

Text #3

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1569. Min Act: -0.0001

Data Index: 1300399 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1620. Min Act: -0.0001

Data Index: 615874 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1595. Min Act: -0.0001

Data Index: 1055008 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1605. Min Act: -0.0001

Data Index: 877410 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1551. Min Act: -0.0001

Data Index: 62261 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1482. Min Act: -0.0001

Data Index: 859812 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1502. Min Act: -0.0001

Data Index: 1417633 (Python Code)

Max Activating Token Index: 888

Text #10

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1446. Min Act: -0.0001

Data Index: 722637 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1412. Min Act: -0.0001

Data Index: 3753 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1409. Min Act: -0.0001

Data Index: 120224 (C4 (Web Text))

Max Activating Token Index: 436

Text #13

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1258. Min Act: -0.0001

Data Index: 968503 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1386. Min Act: -0.0001

Data Index: 1373980 (Python Code)

Max Activating Token Index: 117

Text #15

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1300. Min Act: -0.0001

Data Index: 1592304 (Python Code)

Max Activating Token Index: 137

Text #16

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1349. Min Act: -0.0001

Data Index: 1377585 (Python Code)

Max Activating Token Index: 138

Text #17

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1345. Min Act: -0.0001

Data Index: 1199381 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1331. Min Act: -0.0001

Data Index: 512788 (C4 (Web Text))

Max Activating Token Index: 735

Text #19

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1300. Min Act: -0.0001

Data Index: 1561255 (Python Code)

Max Activating Token Index: 164