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

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

Neuron 1575 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.5002. Min Act: -0.0001

Data Index: 855326 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4975. Min Act: -0.0001

Data Index: 250525 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4634. Min Act: -0.0001

Data Index: 681306 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4778. Min Act: -0.0001

Data Index: 731786 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4597. Min Act: -0.0001

Data Index: 761812 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4707. Min Act: -0.0001

Data Index: 896438 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4470. Min Act: -0.0001

Data Index: 1075363 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4827. Min Act: -0.0001

Data Index: 1321216 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4782. Min Act: -0.0001

Data Index: 235738 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4772. Min Act: -0.0001

Data Index: 1292432 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4640. Min Act: -0.0001

Data Index: 879998 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4728. Min Act: -0.0001

Data Index: 11513 (C4 (Web Text))

Max Activating Token Index: 824

Text #12

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4421. Min Act: -0.0001

Data Index: 1012363 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4392. Min Act: -0.0001

Data Index: 1290371 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4196. Min Act: -0.0001

Data Index: 432134 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4489. Min Act: -0.0001

Data Index: 191780 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4596. Min Act: -0.0001

Data Index: 1134748 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4012. Min Act: -0.0001

Data Index: 272927 (C4 (Web Text))

Max Activating Token Index: 994

Text #18

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4294. Min Act: -0.0001

Data Index: 303315 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4403. Min Act: -0.0001

Data Index: 729681 (C4 (Web Text))

Max Activating Token Index: 543