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

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

Neuron 3861 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.6695. Min Act: -0.0000

Data Index: 944937 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.6093. Min Act: -0.0000

Data Index: 730207 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.5519. Min Act: -0.0000

Data Index: 77845 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.5252. Min Act: -0.0000

Data Index: 677016 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.5383. Min Act: -0.0000

Data Index: 1075148 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.5524. Min Act: -0.0000

Data Index: 164493 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.5094. Min Act: -0.0000

Data Index: 944809 (C4 (Web Text))

Max Activating Token Index: 571

Text #7

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4940. Min Act: -0.0000

Data Index: 26362 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4860. Min Act: -0.0000

Data Index: 1052069 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.5088. Min Act: -0.0000

Data Index: 1029199 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4877. Min Act: -0.0000

Data Index: 660643 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4779. Min Act: -0.0000

Data Index: 941141 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4468. Min Act: -0.0000

Data Index: 133080 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4488. Min Act: -0.0000

Data Index: 520300 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4269. Min Act: -0.0000

Data Index: 117504 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4423. Min Act: -0.0000

Data Index: 655491 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4251. Min Act: -0.0000

Data Index: 155733 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4372. Min Act: -0.0000

Data Index: 466854 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4389. Min Act: -0.0000

Data Index: 901080 (C4 (Web Text))

Max Activating Token Index: 967

Text #19

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4210. Min Act: -0.0000

Data Index: 964245 (C4 (Web Text))

Max Activating Token Index: 804