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

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

Neuron 215 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.6503. Min Act: -0.0001

Data Index: 387319 (C4 (Web Text))

Max Activating Token Index: 737

Text #1

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.6369. Min Act: -0.0001

Data Index: 186331 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.6032. Min Act: -0.0001

Data Index: 448730 (C4 (Web Text))

Max Activating Token Index: 567

Text #3

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.6195. Min Act: -0.0001

Data Index: 1075009 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.5957. Min Act: -0.0001

Data Index: 575119 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.5476. Min Act: -0.0001

Data Index: 1286953 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.5812. Min Act: -0.0001

Data Index: 851213 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.5818. Min Act: -0.0001

Data Index: 36527 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.5806. Min Act: -0.0001

Data Index: 166007 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.5891. Min Act: -0.0001

Data Index: 1167894 (C4 (Web Text))

Max Activating Token Index: 263

Text #10

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.5729. Min Act: -0.0001

Data Index: 1455143 (Python Code)

Max Activating Token Index: 497

Text #11

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.5473. Min Act: -0.0001

Data Index: 285598 (C4 (Web Text))

Max Activating Token Index: 809

Text #12

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.5498. Min Act: -0.0001

Data Index: 689758 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.5844. Min Act: -0.0001

Data Index: 339549 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.5259. Min Act: -0.0001

Data Index: 1348130 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.5273. Min Act: -0.0001

Data Index: 820105 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.5592. Min Act: -0.0001

Data Index: 296909 (C4 (Web Text))

Max Activating Token Index: 724

Text #17

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.5555. Min Act: -0.0001

Data Index: 642004 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.5500. Min Act: -0.0001

Data Index: 1481590 (Python Code)

Max Activating Token Index: 89

Text #19

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.5225. Min Act: -0.0001

Data Index: 611327 (C4 (Web Text))

Max Activating Token Index: 736