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

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

Neuron 3245 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.9743. Min Act: -0.0000

Data Index: 19909 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 1.0025. Min Range: -1.0025

Max Act: 1.0025. Min Act: -0.0000

Data Index: 492652 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.9299. Min Act: -0.0000

Data Index: 983006 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.9737. Min Act: -0.0000

Data Index: 1189245 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.9472. Min Act: -0.0000

Data Index: 1176936 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.8263. Min Act: -0.0000

Data Index: 331443 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.7782. Min Act: -0.0000

Data Index: 281130 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.6980. Min Act: -0.0000

Data Index: 136518 (C4 (Web Text))

Max Activating Token Index: 434

Text #8

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.8021. Min Act: -0.0000

Data Index: 526621 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.7346. Min Act: -0.0000

Data Index: 760493 (C4 (Web Text))

Max Activating Token Index: 227

Text #10

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.6538. Min Act: -0.0000

Data Index: 177005 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.6945. Min Act: -0.0000

Data Index: 973012 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.4577. Min Act: -0.0000

Data Index: 1058135 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.6266. Min Act: -0.0000

Data Index: 546904 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.6401. Min Act: -0.0000

Data Index: 351622 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.7012. Min Act: -0.0000

Data Index: 1544540 (Python Code)

Max Activating Token Index: 699

Text #16

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.6686. Min Act: -0.0000

Data Index: 687321 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.6456. Min Act: -0.0000

Data Index: 664599 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.6609. Min Act: -0.0000

Data Index: 1200466 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.5214. Min Act: -0.0000

Data Index: 1354291 (C4 (Web Text))

Max Activating Token Index: 806