Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 42 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0950. Min Act: -0.0003

Data Index: 107606 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0974. Min Act: -0.0003

Data Index: 1033913 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0968. Min Act: -0.0003

Data Index: 1270844 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0886. Min Act: -0.0003

Data Index: 1294204 (C4 (Web Text))

Max Activating Token Index: 676

Text #4

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0887. Min Act: -0.0003

Data Index: 90677 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0849. Min Act: -0.0003

Data Index: 282018 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0848. Min Act: -0.0003

Data Index: 1076651 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0832. Min Act: -0.0003

Data Index: 497796 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0853. Min Act: -0.0004

Data Index: 490375 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0842. Min Act: -0.0003

Data Index: 845956 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0845. Min Act: -0.0003

Data Index: 944063 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0834. Min Act: -0.0002

Data Index: 1058594 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0822. Min Act: -0.0003

Data Index: 353417 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0808. Min Act: -0.0003

Data Index: 340847 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0808. Min Act: -0.0003

Data Index: 1183149 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0791. Min Act: -0.0003

Data Index: 967658 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0785. Min Act: -0.0003

Data Index: 812964 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0776. Min Act: -0.0003

Data Index: 264497 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0757. Min Act: -0.0003

Data Index: 544326 (C4 (Web Text))

Max Activating Token Index: 937

Text #19

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0768. Min Act: -0.0003

Data Index: 1094355 (C4 (Web Text))

Max Activating Token Index: 912