Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 688 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.9196. Min Range: -2.9196

Max Act: 2.9196. Min Act: -0.0000

Data Index: 640859 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 2.9196. Min Range: -2.9196

Max Act: 1.9733. Min Act: -0.0000

Data Index: 323974 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 2.9196. Min Range: -2.9196

Max Act: 1.9886. Min Act: -0.0000

Data Index: 1128881 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 2.9196. Min Range: -2.9196

Max Act: 1.8029. Min Act: -0.0000

Data Index: 237487 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 2.9196. Min Range: -2.9196

Max Act: 1.8340. Min Act: -0.0000

Data Index: 536719 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 2.9196. Min Range: -2.9196

Max Act: 1.7684. Min Act: -0.0000

Data Index: 616748 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 2.9196. Min Range: -2.9196

Max Act: 1.7270. Min Act: -0.0000

Data Index: 684311 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 2.9196. Min Range: -2.9196

Max Act: 1.7034. Min Act: -0.0000

Data Index: 1308183 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 2.9196. Min Range: -2.9196

Max Act: 1.7053. Min Act: -0.0000

Data Index: 423319 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 2.9196. Min Range: -2.9196

Max Act: 1.6805. Min Act: -0.0000

Data Index: 1316003 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 2.9196. Min Range: -2.9196

Max Act: 1.6338. Min Act: -0.0000

Data Index: 699408 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 2.9196. Min Range: -2.9196

Max Act: 1.5416. Min Act: -0.0000

Data Index: 651227 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 2.9196. Min Range: -2.9196

Max Act: 1.4791. Min Act: -0.0000

Data Index: 772425 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 2.9196. Min Range: -2.9196

Max Act: 1.6993. Min Act: -0.0000

Data Index: 1305213 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 2.9196. Min Range: -2.9196

Max Act: 1.4973. Min Act: -0.0000

Data Index: 625660 (C4 (Web Text))

Max Activating Token Index: 298

Text #15

Max Range: 2.9196. Min Range: -2.9196

Max Act: 1.4712. Min Act: -0.0000

Data Index: 480702 (C4 (Web Text))

Max Activating Token Index: 721

Text #16

Max Range: 2.9196. Min Range: -2.9196

Max Act: 1.5339. Min Act: -0.0000

Data Index: 191390 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 2.9196. Min Range: -2.9196

Max Act: 1.4613. Min Act: -0.0000

Data Index: 332411 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 2.9196. Min Range: -2.9196

Max Act: 1.4913. Min Act: -0.0000

Data Index: 770114 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 2.9196. Min Range: -2.9196

Max Act: 1.5337. Min Act: -0.0000

Data Index: 373889 (C4 (Web Text))

Max Activating Token Index: 975