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

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

Neuron 1154 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1636. Min Range: -1.1636

Max Act: 1.1636. Min Act: -0.0002

Data Index: 452843 (C4 (Web Text))

Max Activating Token Index: 188

Text #1

Max Range: 1.1636. Min Range: -1.1636

Max Act: 1.1281. Min Act: -0.0002

Data Index: 267593 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 1.1636. Min Range: -1.1636

Max Act: 1.1137. Min Act: -0.0002

Data Index: 204015 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 1.1636. Min Range: -1.1636

Max Act: 1.0847. Min Act: -0.0002

Data Index: 1156769 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 1.1636. Min Range: -1.1636

Max Act: 1.0408. Min Act: -0.0002

Data Index: 920540 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 1.1636. Min Range: -1.1636

Max Act: 1.0393. Min Act: -0.0002

Data Index: 1008090 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 1.1636. Min Range: -1.1636

Max Act: 1.0029. Min Act: -0.0002

Data Index: 1285810 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 1.1636. Min Range: -1.1636

Max Act: 1.0500. Min Act: -0.0002

Data Index: 1331940 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 1.1636. Min Range: -1.1636

Max Act: 1.0152. Min Act: -0.0002

Data Index: 1252453 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.9597. Min Act: -0.0002

Data Index: 572312 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.9819. Min Act: -0.0002

Data Index: 926310 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.9823. Min Act: -0.0002

Data Index: 952012 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 1.1636. Min Range: -1.1636

Max Act: 1.0411. Min Act: -0.0002

Data Index: 624426 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 1.1636. Min Range: -1.1636

Max Act: 1.0396. Min Act: -0.0002

Data Index: 812503 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.9789. Min Act: -0.0002

Data Index: 563843 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.9767. Min Act: -0.0002

Data Index: 12449 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.9677. Min Act: -0.0002

Data Index: 70223 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.9579. Min Act: -0.0002

Data Index: 1009624 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.9629. Min Act: -0.0002

Data Index: 1281617 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.9913. Min Act: -0.0002

Data Index: 1244551 (C4 (Web Text))

Max Activating Token Index: 91