Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 760 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0844. Min Act: -0.0003

Data Index: 267925 (C4 (Web Text))

Max Activating Token Index: 522

Text #1

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0846. Min Act: -0.0003

Data Index: 561484 (C4 (Web Text))

Max Activating Token Index: 788

Text #2

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0930. Min Act: -0.0003

Data Index: 373224 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0864. Min Act: -0.0003

Data Index: 237790 (C4 (Web Text))

Max Activating Token Index: 737

Text #4

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0853. Min Act: -0.0003

Data Index: 162551 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0810. Min Act: -0.0003

Data Index: 1235328 (C4 (Web Text))

Max Activating Token Index: 521

Text #6

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0796. Min Act: -0.0003

Data Index: 929437 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0796. Min Act: -0.0003

Data Index: 1077811 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0828. Min Act: -0.0003

Data Index: 398913 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0703. Min Act: -0.0003

Data Index: 1013210 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0676. Min Act: -0.0003

Data Index: 889862 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0807. Min Act: -0.0003

Data Index: 1329974 (C4 (Web Text))

Max Activating Token Index: 552

Text #12

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0802. Min Act: -0.0003

Data Index: 1076124 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0763. Min Act: -0.0003

Data Index: 574792 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0746. Min Act: -0.0003

Data Index: 464893 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0758. Min Act: -0.0003

Data Index: 761815 (C4 (Web Text))

Max Activating Token Index: 628

Text #16

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0762. Min Act: -0.0003

Data Index: 117347 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0755. Min Act: -0.0003

Data Index: 852809 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0735. Min Act: -0.0003

Data Index: 227120 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0797. Min Act: -0.0003

Data Index: 85478 (C4 (Web Text))

Max Activating Token Index: 570