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

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

Neuron 2598 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3130. Min Range: -1.3130

Max Act: 1.3130. Min Act: -0.0001

Data Index: 424549 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 1.3130. Min Range: -1.3130

Max Act: 1.1858. Min Act: -0.0001

Data Index: 828239 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 1.3130. Min Range: -1.3130

Max Act: 1.0318. Min Act: -0.0001

Data Index: 1172396 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 1.3130. Min Range: -1.3130

Max Act: 1.0317. Min Act: -0.0001

Data Index: 846667 (C4 (Web Text))

Max Activating Token Index: 593

Text #4

Max Range: 1.3130. Min Range: -1.3130

Max Act: 1.0430. Min Act: -0.0001

Data Index: 927065 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 1.3130. Min Range: -1.3130

Max Act: 1.0043. Min Act: -0.0001

Data Index: 299544 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 1.3130. Min Range: -1.3130

Max Act: 1.0006. Min Act: -0.0001

Data Index: 120823 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 1.3130. Min Range: -1.3130

Max Act: 0.9719. Min Act: -0.0001

Data Index: 1114007 (C4 (Web Text))

Max Activating Token Index: 583

Text #8

Max Range: 1.3130. Min Range: -1.3130

Max Act: 0.9528. Min Act: -0.0002

Data Index: 1219162 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 1.3130. Min Range: -1.3130

Max Act: 1.0149. Min Act: -0.0001

Data Index: 1099328 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 1.3130. Min Range: -1.3130

Max Act: 1.0028. Min Act: -0.0002

Data Index: 1235696 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 1.3130. Min Range: -1.3130

Max Act: 0.9719. Min Act: -0.0001

Data Index: 511788 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 1.3130. Min Range: -1.3130

Max Act: 0.9844. Min Act: -0.0002

Data Index: 371848 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 1.3130. Min Range: -1.3130

Max Act: 0.9321. Min Act: -0.0002

Data Index: 58574 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 1.3130. Min Range: -1.3130

Max Act: 0.8706. Min Act: -0.0001

Data Index: 38994 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 1.3130. Min Range: -1.3130

Max Act: 1.0219. Min Act: -0.0001

Data Index: 1308478 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 1.3130. Min Range: -1.3130

Max Act: 0.9470. Min Act: -0.0002

Data Index: 277742 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 1.3130. Min Range: -1.3130

Max Act: 0.8858. Min Act: -0.0002

Data Index: 1097777 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 1.3130. Min Range: -1.3130

Max Act: 0.9419. Min Act: -0.0001

Data Index: 677419 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 1.3130. Min Range: -1.3130

Max Act: 0.9003. Min Act: -0.0002

Data Index: 313964 (C4 (Web Text))

Max Activating Token Index: 290