Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3034 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3482. Min Range: -1.3482

Max Act: 1.3482. Min Act: -0.0001

Data Index: 1050929 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 1.3482. Min Range: -1.3482

Max Act: 1.3224. Min Act: -0.0000

Data Index: 1131330 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 1.3482. Min Range: -1.3482

Max Act: 1.2235. Min Act: -0.0001

Data Index: 29892 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 1.3482. Min Range: -1.3482

Max Act: 1.2541. Min Act: -0.0000

Data Index: 981928 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 1.3482. Min Range: -1.3482

Max Act: 1.1242. Min Act: -0.0000

Data Index: 37840 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 1.3482. Min Range: -1.3482

Max Act: 1.1689. Min Act: -0.0000

Data Index: 476431 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 1.3482. Min Range: -1.3482

Max Act: 1.1199. Min Act: -0.0000

Data Index: 1112011 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 1.3482. Min Range: -1.3482

Max Act: 1.1383. Min Act: -0.0000

Data Index: 1342182 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 1.3482. Min Range: -1.3482

Max Act: 1.0061. Min Act: -0.0001

Data Index: 639474 (C4 (Web Text))

Max Activating Token Index: 868

Text #9

Max Range: 1.3482. Min Range: -1.3482

Max Act: 1.0270. Min Act: -0.0000

Data Index: 968542 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 1.3482. Min Range: -1.3482

Max Act: 1.0218. Min Act: -0.0000

Data Index: 119512 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 1.3482. Min Range: -1.3482

Max Act: 0.9702. Min Act: -0.0000

Data Index: 921352 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 1.3482. Min Range: -1.3482

Max Act: 0.8597. Min Act: -0.0000

Data Index: 723749 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 1.3482. Min Range: -1.3482

Max Act: 0.9577. Min Act: -0.0000

Data Index: 1082438 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 1.3482. Min Range: -1.3482

Max Act: 0.8220. Min Act: -0.0000

Data Index: 1180493 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 1.3482. Min Range: -1.3482

Max Act: 0.9331. Min Act: -0.0000

Data Index: 996681 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 1.3482. Min Range: -1.3482

Max Act: 0.9047. Min Act: -0.0001

Data Index: 1082980 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 1.3482. Min Range: -1.3482

Max Act: 0.8940. Min Act: -0.0000

Data Index: 1226873 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 1.3482. Min Range: -1.3482

Max Act: 0.9212. Min Act: -0.0001

Data Index: 749715 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 1.3482. Min Range: -1.3482

Max Act: 0.9434. Min Act: -0.0000

Data Index: 987524 (C4 (Web Text))

Max Activating Token Index: 68