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

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

Neuron 1033 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: 0.0978. Min Range: -0.0978

Max Act: 0.0978. Min Act: -0.0003

Data Index: 987885 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0934. Min Act: -0.0003

Data Index: 1049385 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0867. Min Act: -0.0003

Data Index: 1220726 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0887. Min Act: -0.0003

Data Index: 578946 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0919. Min Act: -0.0003

Data Index: 408816 (C4 (Web Text))

Max Activating Token Index: 161

Text #5

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0865. Min Act: -0.0003

Data Index: 1294914 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0886. Min Act: -0.0003

Data Index: 688919 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0879. Min Act: -0.0003

Data Index: 1342083 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0901. Min Act: -0.0003

Data Index: 1026316 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0866. Min Act: -0.0003

Data Index: 1233700 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0904. Min Act: -0.0003

Data Index: 1308606 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0900. Min Act: -0.0003

Data Index: 717047 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0821. Min Act: -0.0003

Data Index: 71681 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0861. Min Act: -0.0003

Data Index: 1335835 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0910. Min Act: -0.0003

Data Index: 511542 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0831. Min Act: -0.0003

Data Index: 965613 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0854. Min Act: -0.0003

Data Index: 1060696 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0817. Min Act: -0.0003

Data Index: 444676 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0822. Min Act: -0.0003

Data Index: 1023228 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0868. Min Act: -0.0003

Data Index: 850648 (C4 (Web Text))

Max Activating Token Index: 265