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

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

Neuron 3210 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7212. Min Range: -2.7212

Max Act: 2.7212. Min Act: -0.0000

Data Index: 69948 (C4 (Web Text))

Max Activating Token Index: 698

Text #1

Max Range: 2.7212. Min Range: -2.7212

Max Act: 2.6843. Min Act: -0.0000

Data Index: 93989 (C4 (Web Text))

Max Activating Token Index: 618

Text #2

Max Range: 2.7212. Min Range: -2.7212

Max Act: 2.6171. Min Act: -0.0000

Data Index: 595718 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 2.7212. Min Range: -2.7212

Max Act: 2.7111. Min Act: -0.0000

Data Index: 362829 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 2.7212. Min Range: -2.7212

Max Act: 2.4410. Min Act: -0.0000

Data Index: 1349887 (C4 (Web Text))

Max Activating Token Index: 836

Text #5

Max Range: 2.7212. Min Range: -2.7212

Max Act: 2.6667. Min Act: -0.0000

Data Index: 470127 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 2.7212. Min Range: -2.7212

Max Act: 2.5210. Min Act: -0.0000

Data Index: 402405 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 2.7212. Min Range: -2.7212

Max Act: 2.5038. Min Act: -0.0000

Data Index: 475441 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 2.7212. Min Range: -2.7212

Max Act: 2.4952. Min Act: -0.0000

Data Index: 297242 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 2.7212. Min Range: -2.7212

Max Act: 2.3540. Min Act: -0.0000

Data Index: 902121 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 2.7212. Min Range: -2.7212

Max Act: 2.4572. Min Act: -0.0000

Data Index: 936610 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 2.7212. Min Range: -2.7212

Max Act: 2.4468. Min Act: -0.0000

Data Index: 327170 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 2.7212. Min Range: -2.7212

Max Act: 2.4356. Min Act: -0.0000

Data Index: 372090 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 2.7212. Min Range: -2.7212

Max Act: 2.4057. Min Act: -0.0000

Data Index: 929569 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 2.7212. Min Range: -2.7212

Max Act: 2.2890. Min Act: -0.0000

Data Index: 1201829 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 2.7212. Min Range: -2.7212

Max Act: 2.3908. Min Act: -0.0000

Data Index: 152091 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 2.7212. Min Range: -2.7212

Max Act: 2.2576. Min Act: -0.0000

Data Index: 1150850 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 2.7212. Min Range: -2.7212

Max Act: 1.9507. Min Act: -0.0000

Data Index: 304016 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 2.7212. Min Range: -2.7212

Max Act: 2.3745. Min Act: -0.0000

Data Index: 744588 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 2.7212. Min Range: -2.7212

Max Act: 2.3835. Min Act: -0.0000

Data Index: 626843 (C4 (Web Text))

Max Activating Token Index: 438