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

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

Neuron 5405 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.6079. Min Act: -0.0001

Data Index: 1089142 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.0268. Min Act: -0.0001

Data Index: 995945 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.1825. Min Act: -0.0001

Data Index: 706057 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.0356. Min Act: -0.0000

Data Index: 49797 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.0426. Min Act: -0.0001

Data Index: 783814 (C4 (Web Text))

Max Activating Token Index: 896

Text #5

Max Range: 1.6079. Min Range: -1.6079

Max Act: 0.8675. Min Act: -0.0001

Data Index: 701212 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.0252. Min Act: -0.0001

Data Index: 647563 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 1.6079. Min Range: -1.6079

Max Act: 0.9255. Min Act: -0.0001

Data Index: 137438 (C4 (Web Text))

Max Activating Token Index: 484

Text #8

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.0998. Min Act: -0.0000

Data Index: 133553 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.0120. Min Act: -0.0001

Data Index: 1346400 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.0414. Min Act: -0.0001

Data Index: 754653 (C4 (Web Text))

Max Activating Token Index: 317

Text #11

Max Range: 1.6079. Min Range: -1.6079

Max Act: 0.8925. Min Act: -0.0001

Data Index: 1124091 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 1.6079. Min Range: -1.6079

Max Act: 0.8613. Min Act: -0.0001

Data Index: 174551 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 1.6079. Min Range: -1.6079

Max Act: 0.8209. Min Act: -0.0001

Data Index: 39457 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 1.6079. Min Range: -1.6079

Max Act: 1.0102. Min Act: -0.0001

Data Index: 250611 (C4 (Web Text))

Max Activating Token Index: 656

Text #15

Max Range: 1.6079. Min Range: -1.6079

Max Act: 0.9101. Min Act: -0.0000

Data Index: 258046 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 1.6079. Min Range: -1.6079

Max Act: 0.9692. Min Act: -0.0001

Data Index: 3280 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 1.6079. Min Range: -1.6079

Max Act: 0.8524. Min Act: -0.0001

Data Index: 750226 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 1.6079. Min Range: -1.6079

Max Act: 0.7595. Min Act: -0.0001

Data Index: 701061 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 1.6079. Min Range: -1.6079

Max Act: 0.8194. Min Act: -0.0001

Data Index: 796901 (C4 (Web Text))

Max Activating Token Index: 541