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

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

Neuron 4636 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.3281. Min Range: -2.3281

Max Act: 2.3281. Min Act: -0.0000

Data Index: 504818 (C4 (Web Text))

Max Activating Token Index: 454

Text #1

Max Range: 2.3281. Min Range: -2.3281

Max Act: 1.9453. Min Act: -0.0000

Data Index: 369944 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 2.3281. Min Range: -2.3281

Max Act: 1.7692. Min Act: -0.0000

Data Index: 189687 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 2.3281. Min Range: -2.3281

Max Act: 1.6598. Min Act: -0.0000

Data Index: 331926 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 2.3281. Min Range: -2.3281

Max Act: 1.7038. Min Act: -0.0000

Data Index: 29840 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 2.3281. Min Range: -2.3281

Max Act: 1.6533. Min Act: -0.0000

Data Index: 301656 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 2.3281. Min Range: -2.3281

Max Act: 1.6267. Min Act: -0.0000

Data Index: 632598 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 2.3281. Min Range: -2.3281

Max Act: 1.6189. Min Act: -0.0000

Data Index: 708586 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 2.3281. Min Range: -2.3281

Max Act: 1.6871. Min Act: -0.0000

Data Index: 104450 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 2.3281. Min Range: -2.3281

Max Act: 1.6813. Min Act: -0.0000

Data Index: 584422 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 2.3281. Min Range: -2.3281

Max Act: 1.5875. Min Act: -0.0000

Data Index: 1063898 (C4 (Web Text))

Max Activating Token Index: 995

Text #11

Max Range: 2.3281. Min Range: -2.3281

Max Act: 1.5740. Min Act: -0.0000

Data Index: 214939 (C4 (Web Text))

Max Activating Token Index: 126

Text #12

Max Range: 2.3281. Min Range: -2.3281

Max Act: 1.4880. Min Act: -0.0000

Data Index: 321366 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 2.3281. Min Range: -2.3281

Max Act: 1.5712. Min Act: -0.0000

Data Index: 581021 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 2.3281. Min Range: -2.3281

Max Act: 1.5645. Min Act: -0.0000

Data Index: 1284318 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 2.3281. Min Range: -2.3281

Max Act: 1.2151. Min Act: -0.0000

Data Index: 642338 (C4 (Web Text))

Max Activating Token Index: 947

Text #16

Max Range: 2.3281. Min Range: -2.3281

Max Act: 1.4155. Min Act: -0.0000

Data Index: 876460 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 2.3281. Min Range: -2.3281

Max Act: 1.4780. Min Act: -0.0000

Data Index: 1227230 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 2.3281. Min Range: -2.3281

Max Act: 1.4750. Min Act: -0.0000

Data Index: 7555 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 2.3281. Min Range: -2.3281

Max Act: 1.3003. Min Act: -0.0000

Data Index: 491482 (C4 (Web Text))

Max Activating Token Index: 116