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

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

Neuron 4528 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: 4.9293. Min Range: -4.9293

Max Act: 4.9293. Min Act: -0.0000

Data Index: 850556 (C4 (Web Text))

Max Activating Token Index: 843

Text #1

Max Range: 4.9293. Min Range: -4.9293

Max Act: 3.3774. Min Act: -0.0000

Data Index: 745767 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 4.9293. Min Range: -4.9293

Max Act: 2.9063. Min Act: -0.0000

Data Index: 44938 (C4 (Web Text))

Max Activating Token Index: 567

Text #3

Max Range: 4.9293. Min Range: -4.9293

Max Act: 2.8775. Min Act: -0.0000

Data Index: 204800 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 4.9293. Min Range: -4.9293

Max Act: 3.1155. Min Act: -0.0000

Data Index: 494686 (C4 (Web Text))

Max Activating Token Index: 724

Text #5

Max Range: 4.9293. Min Range: -4.9293

Max Act: 2.8034. Min Act: -0.0000

Data Index: 1251721 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 4.9293. Min Range: -4.9293

Max Act: 2.9112. Min Act: -0.0000

Data Index: 983206 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 4.9293. Min Range: -4.9293

Max Act: 2.7150. Min Act: -0.0000

Data Index: 833917 (C4 (Web Text))

Max Activating Token Index: 653

Text #8

Max Range: 4.9293. Min Range: -4.9293

Max Act: 2.6884. Min Act: -0.0000

Data Index: 911265 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 4.9293. Min Range: -4.9293

Max Act: 2.5255. Min Act: -0.0000

Data Index: 1296103 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 4.9293. Min Range: -4.9293

Max Act: 2.6208. Min Act: -0.0000

Data Index: 995266 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 4.9293. Min Range: -4.9293

Max Act: 2.7412. Min Act: -0.0000

Data Index: 465972 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 4.9293. Min Range: -4.9293

Max Act: 2.6382. Min Act: -0.0000

Data Index: 761521 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 4.9293. Min Range: -4.9293

Max Act: 2.3653. Min Act: -0.0000

Data Index: 965242 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 4.9293. Min Range: -4.9293

Max Act: 2.4063. Min Act: -0.0000

Data Index: 851856 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 4.9293. Min Range: -4.9293

Max Act: 2.3550. Min Act: -0.0000

Data Index: 666371 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 4.9293. Min Range: -4.9293

Max Act: 2.4765. Min Act: -0.0000

Data Index: 734820 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 4.9293. Min Range: -4.9293

Max Act: 2.2029. Min Act: -0.0000

Data Index: 657368 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 4.9293. Min Range: -4.9293

Max Act: 2.0933. Min Act: -0.0000

Data Index: 637756 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 4.9293. Min Range: -4.9293

Max Act: 2.4246. Min Act: -0.0000

Data Index: 144798 (C4 (Web Text))

Max Activating Token Index: 370