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

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

Neuron 63 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.6548. Min Act: -0.0001

Data Index: 876146 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.6781. Min Act: -0.0000

Data Index: 544306 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.7001. Min Act: -0.0001

Data Index: 1579605 (Python Code)

Max Activating Token Index: 542

Text #3

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.6037. Min Act: -0.0001

Data Index: 1653310 (Python Code)

Max Activating Token Index: 502

Text #4

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.5892. Min Act: -0.0001

Data Index: 1427384 (Python Code)

Max Activating Token Index: 605

Text #5

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.6125. Min Act: -0.0001

Data Index: 1640313 (Python Code)

Max Activating Token Index: 664

Text #6

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.5799. Min Act: -0.0001

Data Index: 1422009 (Python Code)

Max Activating Token Index: 941

Text #7

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.5762. Min Act: -0.0000

Data Index: 67572 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.5569. Min Act: -0.0001

Data Index: 1556285 (Python Code)

Max Activating Token Index: 493

Text #9

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.5397. Min Act: -0.0001

Data Index: 1468705 (Python Code)

Max Activating Token Index: 540

Text #10

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.5738. Min Act: -0.0001

Data Index: 936639 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.5382. Min Act: -0.0000

Data Index: 292528 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.5213. Min Act: -0.0001

Data Index: 610531 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.5337. Min Act: -0.0000

Data Index: 587775 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.5019. Min Act: -0.0001

Data Index: 456400 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.5692. Min Act: -0.0001

Data Index: 1407278 (Python Code)

Max Activating Token Index: 466

Text #16

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.5125. Min Act: -0.0001

Data Index: 1399931 (Python Code)

Max Activating Token Index: 422

Text #17

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.5072. Min Act: -0.0001

Data Index: 1304286 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.5250. Min Act: -0.0001

Data Index: 1366819 (Python Code)

Max Activating Token Index: 426

Text #19

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.5056. Min Act: -0.0001

Data Index: 1031909 (C4 (Web Text))

Max Activating Token Index: 666