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

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

Neuron 2538 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7590. Min Range: -2.7590

Max Act: 2.7336. Min Act: -0.0000

Data Index: 1036704 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 2.7590. Min Range: -2.7590

Max Act: 2.6565. Min Act: -0.0000

Data Index: 788611 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 2.7590. Min Range: -2.7590

Max Act: 2.7388. Min Act: -0.0000

Data Index: 923531 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 2.7590. Min Range: -2.7590

Max Act: 2.7217. Min Act: -0.0000

Data Index: 691808 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 2.7590. Min Range: -2.7590

Max Act: 2.7048. Min Act: -0.0000

Data Index: 589404 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 2.7590. Min Range: -2.7590

Max Act: 2.6385. Min Act: -0.0000

Data Index: 385430 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 2.7590. Min Range: -2.7590

Max Act: 2.7590. Min Act: -0.0000

Data Index: 199065 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 2.7590. Min Range: -2.7590

Max Act: 2.5704. Min Act: -0.0000

Data Index: 976388 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 2.7590. Min Range: -2.7590

Max Act: 2.4306. Min Act: -0.0000

Data Index: 340893 (C4 (Web Text))

Max Activating Token Index: 991

Text #9

Max Range: 2.7590. Min Range: -2.7590

Max Act: 2.6758. Min Act: -0.0000

Data Index: 358800 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 2.7590. Min Range: -2.7590

Max Act: 2.5449. Min Act: -0.0000

Data Index: 1180012 (C4 (Web Text))

Max Activating Token Index: 932

Text #11

Max Range: 2.7590. Min Range: -2.7590

Max Act: 2.5554. Min Act: -0.0000

Data Index: 1071145 (C4 (Web Text))

Max Activating Token Index: 989

Text #12

Max Range: 2.7590. Min Range: -2.7590

Max Act: 2.6203. Min Act: -0.0000

Data Index: 599914 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 2.7590. Min Range: -2.7590

Max Act: 2.5195. Min Act: -0.0000

Data Index: 322645 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 2.7590. Min Range: -2.7590

Max Act: 2.4947. Min Act: -0.0000

Data Index: 521487 (C4 (Web Text))

Max Activating Token Index: 1015

Text #15

Max Range: 2.7590. Min Range: -2.7590

Max Act: 2.6199. Min Act: -0.0000

Data Index: 559594 (C4 (Web Text))

Max Activating Token Index: 482

Text #16

Max Range: 2.7590. Min Range: -2.7590

Max Act: 2.4998. Min Act: -0.0000

Data Index: 744634 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 2.7590. Min Range: -2.7590

Max Act: 2.4568. Min Act: -0.0000

Data Index: 1264267 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 2.7590. Min Range: -2.7590

Max Act: 2.4825. Min Act: -0.0000

Data Index: 625585 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 2.7590. Min Range: -2.7590

Max Act: 2.4642. Min Act: -0.0000

Data Index: 972189 (C4 (Web Text))

Max Activating Token Index: 53