Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 64 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.1050. Min Act: -0.0003

Data Index: 419447 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.1054. Min Act: -0.0003

Data Index: 142444 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.1000. Min Act: -0.0003

Data Index: 248023 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.1029. Min Act: -0.0003

Data Index: 58938 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0978. Min Act: -0.0003

Data Index: 639513 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0930. Min Act: -0.0003

Data Index: 1328504 (C4 (Web Text))

Max Activating Token Index: 252

Text #6

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0853. Min Act: -0.0003

Data Index: 1121423 (C4 (Web Text))

Max Activating Token Index: 668

Text #7

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0938. Min Act: -0.0003

Data Index: 14653 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0898. Min Act: -0.0003

Data Index: 661386 (C4 (Web Text))

Max Activating Token Index: 198

Text #9

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0864. Min Act: -0.0003

Data Index: 69727 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0841. Min Act: -0.0003

Data Index: 640590 (C4 (Web Text))

Max Activating Token Index: 548

Text #11

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0899. Min Act: -0.0003

Data Index: 319463 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0797. Min Act: -0.0003

Data Index: 492827 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0830. Min Act: -0.0003

Data Index: 543041 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0854. Min Act: -0.0003

Data Index: 898879 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0853. Min Act: -0.0003

Data Index: 1205782 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0875. Min Act: -0.0003

Data Index: 169292 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0836. Min Act: -0.0003

Data Index: 1031161 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0830. Min Act: -0.0003

Data Index: 462522 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0819. Min Act: -0.0003

Data Index: 543935 (C4 (Web Text))

Max Activating Token Index: 930