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

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

Neuron 3521 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: 1.0315. Min Range: -1.0315

Max Act: 1.0315. Min Act: -0.0001

Data Index: 594443 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 1.0315. Min Range: -1.0315

Max Act: 0.9002. Min Act: -0.0001

Data Index: 178114 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 1.0315. Min Range: -1.0315

Max Act: 0.8526. Min Act: -0.0001

Data Index: 481446 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 1.0315. Min Range: -1.0315

Max Act: 0.9455. Min Act: -0.0001

Data Index: 578803 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 1.0315. Min Range: -1.0315

Max Act: 0.8745. Min Act: -0.0001

Data Index: 703544 (C4 (Web Text))

Max Activating Token Index: 612

Text #5

Max Range: 1.0315. Min Range: -1.0315

Max Act: 0.8582. Min Act: -0.0001

Data Index: 943745 (C4 (Web Text))

Max Activating Token Index: 3

Text #6

Max Range: 1.0315. Min Range: -1.0315

Max Act: 0.7561. Min Act: -0.0001

Data Index: 406101 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 1.0315. Min Range: -1.0315

Max Act: 0.8226. Min Act: -0.0001

Data Index: 1198603 (C4 (Web Text))

Max Activating Token Index: 379

Text #8

Max Range: 1.0315. Min Range: -1.0315

Max Act: 0.8289. Min Act: -0.0001

Data Index: 1310369 (C4 (Web Text))

Max Activating Token Index: 494

Text #9

Max Range: 1.0315. Min Range: -1.0315

Max Act: 0.8935. Min Act: -0.0001

Data Index: 342174 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 1.0315. Min Range: -1.0315

Max Act: 0.8692. Min Act: -0.0001

Data Index: 1129501 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 1.0315. Min Range: -1.0315

Max Act: 0.7154. Min Act: -0.0001

Data Index: 101908 (C4 (Web Text))

Max Activating Token Index: 374

Text #12

Max Range: 1.0315. Min Range: -1.0315

Max Act: 0.8618. Min Act: -0.0001

Data Index: 739695 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 1.0315. Min Range: -1.0315

Max Act: 0.7623. Min Act: -0.0001

Data Index: 330963 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 1.0315. Min Range: -1.0315

Max Act: 0.7679. Min Act: -0.0001

Data Index: 851766 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 1.0315. Min Range: -1.0315

Max Act: 0.7929. Min Act: -0.0001

Data Index: 193583 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 1.0315. Min Range: -1.0315

Max Act: 0.7859. Min Act: -0.0001

Data Index: 447295 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 1.0315. Min Range: -1.0315

Max Act: 0.7518. Min Act: -0.0001

Data Index: 993418 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 1.0315. Min Range: -1.0315

Max Act: 0.7622. Min Act: -0.0001

Data Index: 664008 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 1.0315. Min Range: -1.0315

Max Act: 0.7548. Min Act: -0.0001

Data Index: 124293 (C4 (Web Text))

Max Activating Token Index: 80