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

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

Neuron 3880 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: 3.6866. Min Range: -3.6866

Max Act: 3.6866. Min Act: -0.0000

Data Index: 80470 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 3.6866. Min Range: -3.6866

Max Act: 3.5437. Min Act: -0.0000

Data Index: 184965 (C4 (Web Text))

Max Activating Token Index: 532

Text #2

Max Range: 3.6866. Min Range: -3.6866

Max Act: 3.0978. Min Act: -0.0000

Data Index: 1074097 (C4 (Web Text))

Max Activating Token Index: 683

Text #3

Max Range: 3.6866. Min Range: -3.6866

Max Act: 3.0086. Min Act: -0.0000

Data Index: 218646 (C4 (Web Text))

Max Activating Token Index: 468

Text #4

Max Range: 3.6866. Min Range: -3.6866

Max Act: 2.7678. Min Act: -0.0000

Data Index: 716827 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 3.6866. Min Range: -3.6866

Max Act: 2.9908. Min Act: -0.0000

Data Index: 458331 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 3.6866. Min Range: -3.6866

Max Act: 2.8531. Min Act: -0.0000

Data Index: 34688 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 3.6866. Min Range: -3.6866

Max Act: 2.6979. Min Act: -0.0000

Data Index: 974766 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 3.6866. Min Range: -3.6866

Max Act: 2.7936. Min Act: -0.0000

Data Index: 54758 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 3.6866. Min Range: -3.6866

Max Act: 2.8147. Min Act: -0.0000

Data Index: 830699 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 3.6866. Min Range: -3.6866

Max Act: 2.7556. Min Act: -0.0000

Data Index: 742387 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 3.6866. Min Range: -3.6866

Max Act: 2.5763. Min Act: -0.0000

Data Index: 1325319 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 3.6866. Min Range: -3.6866

Max Act: 2.5524. Min Act: -0.0000

Data Index: 168250 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 3.6866. Min Range: -3.6866

Max Act: 2.6857. Min Act: -0.0000

Data Index: 1107659 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 3.6866. Min Range: -3.6866

Max Act: 2.5366. Min Act: -0.0000

Data Index: 731470 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 3.6866. Min Range: -3.6866

Max Act: 2.5279. Min Act: -0.0000

Data Index: 953303 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 3.6866. Min Range: -3.6866

Max Act: 2.7817. Min Act: -0.0000

Data Index: 309352 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 3.6866. Min Range: -3.6866

Max Act: 2.6515. Min Act: -0.0000

Data Index: 1037464 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 3.6866. Min Range: -3.6866

Max Act: 2.7729. Min Act: -0.0000

Data Index: 632102 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 3.6866. Min Range: -3.6866

Max Act: 2.6013. Min Act: -0.0000

Data Index: 868028 (C4 (Web Text))

Max Activating Token Index: 174