Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3844 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0934. Min Range: -1.0934

Max Act: 1.0934. Min Act: -0.0000

Data Index: 1475917 (Python Code)

Max Activating Token Index: 695

Text #1

Max Range: 1.0934. Min Range: -1.0934

Max Act: 0.8550. Min Act: -0.0000

Data Index: 1520988 (Python Code)

Max Activating Token Index: 139

Text #2

Max Range: 1.0934. Min Range: -1.0934

Max Act: 0.8150. Min Act: -0.0000

Data Index: 1644117 (Python Code)

Max Activating Token Index: 197

Text #3

Max Range: 1.0934. Min Range: -1.0934

Max Act: 0.8397. Min Act: -0.0000

Data Index: 1114873 (C4 (Web Text))

Max Activating Token Index: 607

Text #4

Max Range: 1.0934. Min Range: -1.0934

Max Act: 0.8590. Min Act: -0.0000

Data Index: 1459292 (Python Code)

Max Activating Token Index: 423

Text #5

Max Range: 1.0934. Min Range: -1.0934

Max Act: 0.8207. Min Act: -0.0000

Data Index: 815733 (C4 (Web Text))

Max Activating Token Index: 453

Text #6

Max Range: 1.0934. Min Range: -1.0934

Max Act: 0.8344. Min Act: -0.0000

Data Index: 633106 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 1.0934. Min Range: -1.0934

Max Act: 0.8286. Min Act: -0.0000

Data Index: 1392570 (Python Code)

Max Activating Token Index: 217

Text #8

Max Range: 1.0934. Min Range: -1.0934

Max Act: 0.8183. Min Act: -0.0000

Data Index: 1384050 (Python Code)

Max Activating Token Index: 477

Text #9

Max Range: 1.0934. Min Range: -1.0934

Max Act: 0.8064. Min Act: -0.0001

Data Index: 692520 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 1.0934. Min Range: -1.0934

Max Act: 0.8057. Min Act: -0.0000

Data Index: 14091 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 1.0934. Min Range: -1.0934

Max Act: 0.7537. Min Act: -0.0000

Data Index: 1163349 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 1.0934. Min Range: -1.0934

Max Act: 0.7696. Min Act: -0.0000

Data Index: 797622 (C4 (Web Text))

Max Activating Token Index: 781

Text #13

Max Range: 1.0934. Min Range: -1.0934

Max Act: 0.7951. Min Act: -0.0000

Data Index: 1404712 (Python Code)

Max Activating Token Index: 109

Text #14

Max Range: 1.0934. Min Range: -1.0934

Max Act: 0.8159. Min Act: -0.0000

Data Index: 1057533 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 1.0934. Min Range: -1.0934

Max Act: 0.7889. Min Act: -0.0000

Data Index: 866691 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 1.0934. Min Range: -1.0934

Max Act: 0.8055. Min Act: -0.0000

Data Index: 1397697 (Python Code)

Max Activating Token Index: 39

Text #17

Max Range: 1.0934. Min Range: -1.0934

Max Act: 0.8071. Min Act: -0.0000

Data Index: 383470 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 1.0934. Min Range: -1.0934

Max Act: 0.7578. Min Act: -0.0000

Data Index: 349956 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 1.0934. Min Range: -1.0934

Max Act: 0.7635. Min Act: -0.0000

Data Index: 142940 (C4 (Web Text))

Max Activating Token Index: 457