Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1147 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0936. Min Act: -0.0002

Data Index: 466471 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0901. Min Act: -0.0002

Data Index: 905456 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0890. Min Act: -0.0001

Data Index: 132414 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0855. Min Act: -0.0000

Data Index: 211976 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0851. Min Act: -0.0003

Data Index: 723740 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0812. Min Act: -0.0003

Data Index: 1572993 (Python Code)

Max Activating Token Index: 194

Text #6

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0806. Min Act: -0.0002

Data Index: 17268 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0808. Min Act: -0.0002

Data Index: 938374 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0825. Min Act: -0.0003

Data Index: 478201 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0816. Min Act: -0.0003

Data Index: 1161609 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0798. Min Act: -0.0002

Data Index: 1306135 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0793. Min Act: -0.0002

Data Index: 712 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0780. Min Act: -0.0000

Data Index: 243080 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0767. Min Act: -0.0001

Data Index: 234328 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0761. Min Act: -0.0002

Data Index: 60550 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0745. Min Act: -0.0002

Data Index: 409607 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0747. Min Act: -0.0003

Data Index: 623603 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0765. Min Act: -0.0003

Data Index: 1209856 (C4 (Web Text))

Max Activating Token Index: 339

Text #18

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0738. Min Act: -0.0002

Data Index: 853524 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0747. Min Act: -0.0002

Data Index: 353995 (C4 (Web Text))

Max Activating Token Index: 717