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

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

Neuron 3906 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: 0.1338. Min Range: -0.1338

Max Act: 0.1268. Min Act: -0.0000

Data Index: 734966 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1338. Min Act: -0.0000

Data Index: 156819 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1201. Min Act: -0.0000

Data Index: 938342 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1188. Min Act: -0.0000

Data Index: 507444 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1108. Min Act: -0.0000

Data Index: 1138200 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1112. Min Act: -0.0000

Data Index: 196832 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1031. Min Act: -0.0000

Data Index: 526669 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1023. Min Act: -0.0000

Data Index: 706083 (C4 (Web Text))

Max Activating Token Index: 547

Text #8

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1019. Min Act: -0.0000

Data Index: 402722 (C4 (Web Text))

Max Activating Token Index: 275

Text #9

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0980. Min Act: -0.0000

Data Index: 292872 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0984. Min Act: -0.0000

Data Index: 1046992 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1012. Min Act: -0.0000

Data Index: 369378 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1003. Min Act: -0.0000

Data Index: 469538 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0993. Min Act: -0.0000

Data Index: 183111 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0945. Min Act: -0.0000

Data Index: 611538 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0875. Min Act: -0.0000

Data Index: 1283483 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0913. Min Act: -0.0000

Data Index: 1177231 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0962. Min Act: -0.0000

Data Index: 87823 (C4 (Web Text))

Max Activating Token Index: 325

Text #18

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0926. Min Act: -0.0000

Data Index: 589288 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0887. Min Act: -0.0000

Data Index: 118603 (C4 (Web Text))

Max Activating Token Index: 780