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

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

Neuron 1531 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: 1.3419. Min Range: -1.3419

Max Act: 1.3419. Min Act: 0.0000

Data Index: 1374871 (Python Code)

Max Activating Token Index: 617

Text #1

Max Range: 1.3419. Min Range: -1.3419

Max Act: 1.3331. Min Act: -0.0000

Data Index: 1064125 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 1.3419. Min Range: -1.3419

Max Act: 1.3041. Min Act: -0.0000

Data Index: 827746 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 1.3419. Min Range: -1.3419

Max Act: 1.1821. Min Act: -0.0000

Data Index: 1372532 (Python Code)

Max Activating Token Index: 208

Text #4

Max Range: 1.3419. Min Range: -1.3419

Max Act: 1.2206. Min Act: -0.0000

Data Index: 1492636 (Python Code)

Max Activating Token Index: 22

Text #5

Max Range: 1.3419. Min Range: -1.3419

Max Act: 1.1652. Min Act: -0.0000

Data Index: 1597800 (Python Code)

Max Activating Token Index: 75

Text #6

Max Range: 1.3419. Min Range: -1.3419

Max Act: 1.1657. Min Act: -0.0000

Data Index: 1505925 (Python Code)

Max Activating Token Index: 176

Text #7

Max Range: 1.3419. Min Range: -1.3419

Max Act: 1.1315. Min Act: -0.0000

Data Index: 1479425 (Python Code)

Max Activating Token Index: 82

Text #8

Max Range: 1.3419. Min Range: -1.3419

Max Act: 1.1578. Min Act: 0.0000

Data Index: 1489177 (Python Code)

Max Activating Token Index: 671

Text #9

Max Range: 1.3419. Min Range: -1.3419

Max Act: 1.2040. Min Act: -0.0000

Data Index: 1368453 (Python Code)

Max Activating Token Index: 14

Text #10

Max Range: 1.3419. Min Range: -1.3419

Max Act: 1.1958. Min Act: -0.0000

Data Index: 1568809 (Python Code)

Max Activating Token Index: 761

Text #11

Max Range: 1.3419. Min Range: -1.3419

Max Act: 1.1640. Min Act: 0.0000

Data Index: 397733 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 1.3419. Min Range: -1.3419

Max Act: 1.1505. Min Act: -0.0000

Data Index: 1518206 (Python Code)

Max Activating Token Index: 644

Text #13

Max Range: 1.3419. Min Range: -1.3419

Max Act: 1.1174. Min Act: -0.0000

Data Index: 1470080 (Python Code)

Max Activating Token Index: 501

Text #14

Max Range: 1.3419. Min Range: -1.3419

Max Act: 1.1574. Min Act: -0.0000

Data Index: 1490869 (Python Code)

Max Activating Token Index: 166

Text #15

Max Range: 1.3419. Min Range: -1.3419

Max Act: 1.1167. Min Act: -0.0000

Data Index: 1468398 (Python Code)

Max Activating Token Index: 87

Text #16

Max Range: 1.3419. Min Range: -1.3419

Max Act: 1.1096. Min Act: -0.0000

Data Index: 1516855 (Python Code)

Max Activating Token Index: 579

Text #17

Max Range: 1.3419. Min Range: -1.3419

Max Act: 1.1282. Min Act: -0.0000

Data Index: 1616375 (Python Code)

Max Activating Token Index: 201

Text #18

Max Range: 1.3419. Min Range: -1.3419

Max Act: 1.0828. Min Act: -0.0000

Data Index: 1462707 (Python Code)

Max Activating Token Index: 222

Text #19

Max Range: 1.3419. Min Range: -1.3419

Max Act: 1.0413. Min Act: 0.0000

Data Index: 1409625 (Python Code)

Max Activating Token Index: 851