Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3650 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.7976. Min Act: -0.0001

Data Index: 1446351 (Python Code)

Max Activating Token Index: 559

Text #1

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.7351. Min Act: -0.0001

Data Index: 1362723 (Python Code)

Max Activating Token Index: 793

Text #2

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.7736. Min Act: -0.0001

Data Index: 1515976 (Python Code)

Max Activating Token Index: 1003

Text #3

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.7235. Min Act: -0.0001

Data Index: 1519842 (Python Code)

Max Activating Token Index: 85

Text #4

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.7038. Min Act: -0.0001

Data Index: 1533958 (Python Code)

Max Activating Token Index: 1000

Text #5

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.7213. Min Act: -0.0001

Data Index: 1411105 (Python Code)

Max Activating Token Index: 686

Text #6

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.7391. Min Act: -0.0001

Data Index: 1543127 (Python Code)

Max Activating Token Index: 206

Text #7

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.7349. Min Act: -0.0001

Data Index: 1377600 (Python Code)

Max Activating Token Index: 911

Text #8

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6780. Min Act: -0.0001

Data Index: 1445411 (Python Code)

Max Activating Token Index: 503

Text #9

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6911. Min Act: -0.0001

Data Index: 1508446 (Python Code)

Max Activating Token Index: 781

Text #10

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.7074. Min Act: -0.0001

Data Index: 1423873 (Python Code)

Max Activating Token Index: 590

Text #11

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6765. Min Act: -0.0001

Data Index: 1636252 (Python Code)

Max Activating Token Index: 45

Text #12

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6472. Min Act: -0.0001

Data Index: 1516790 (Python Code)

Max Activating Token Index: 862

Text #13

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6686. Min Act: -0.0001

Data Index: 1396509 (Python Code)

Max Activating Token Index: 490

Text #14

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6641. Min Act: -0.0001

Data Index: 1587643 (Python Code)

Max Activating Token Index: 836

Text #15

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6638. Min Act: -0.0001

Data Index: 1529654 (Python Code)

Max Activating Token Index: 50

Text #16

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6469. Min Act: -0.0001

Data Index: 1379901 (Python Code)

Max Activating Token Index: 493

Text #17

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6387. Min Act: -0.0001

Data Index: 1559135 (Python Code)

Max Activating Token Index: 166

Text #18

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6617. Min Act: -0.0001

Data Index: 1453451 (Python Code)

Max Activating Token Index: 872

Text #19

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6553. Min Act: -0.0001

Data Index: 1643665 (Python Code)

Max Activating Token Index: 379