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

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

Neuron 1650 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.9954. Min Range: -4.9954

Max Act: 4.9954. Min Act: -0.0000

Data Index: 373300 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 4.9954. Min Range: -4.9954

Max Act: 4.7396. Min Act: -0.0000

Data Index: 688756 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 4.9954. Min Range: -4.9954

Max Act: 4.5031. Min Act: -0.0001

Data Index: 188883 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 4.9954. Min Range: -4.9954

Max Act: 4.4508. Min Act: -0.0001

Data Index: 1238720 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 4.9954. Min Range: -4.9954

Max Act: 4.4117. Min Act: -0.0001

Data Index: 405915 (C4 (Web Text))

Max Activating Token Index: 845

Text #5

Max Range: 4.9954. Min Range: -4.9954

Max Act: 4.2892. Min Act: -0.0000

Data Index: 556623 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 4.9954. Min Range: -4.9954

Max Act: 4.1654. Min Act: -0.0001

Data Index: 352672 (C4 (Web Text))

Max Activating Token Index: 530

Text #7

Max Range: 4.9954. Min Range: -4.9954

Max Act: 4.2372. Min Act: -0.0001

Data Index: 1037945 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 4.9954. Min Range: -4.9954

Max Act: 4.2021. Min Act: -0.0001

Data Index: 269160 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 4.9954. Min Range: -4.9954

Max Act: 4.2607. Min Act: -0.0001

Data Index: 1042066 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 4.9954. Min Range: -4.9954

Max Act: 4.2503. Min Act: -0.0001

Data Index: 1029539 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 4.9954. Min Range: -4.9954

Max Act: 3.9189. Min Act: -0.0001

Data Index: 124504 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 4.9954. Min Range: -4.9954

Max Act: 4.0871. Min Act: -0.0001

Data Index: 791779 (C4 (Web Text))

Max Activating Token Index: 841

Text #13

Max Range: 4.9954. Min Range: -4.9954

Max Act: 4.0954. Min Act: -0.0000

Data Index: 26190 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 4.9954. Min Range: -4.9954

Max Act: 4.0303. Min Act: -0.0001

Data Index: 42365 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 4.9954. Min Range: -4.9954

Max Act: 4.0248. Min Act: -0.0001

Data Index: 1294195 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 4.9954. Min Range: -4.9954

Max Act: 4.1415. Min Act: -0.0001

Data Index: 1204630 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 4.9954. Min Range: -4.9954

Max Act: 4.3653. Min Act: -0.0000

Data Index: 64033 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 4.9954. Min Range: -4.9954

Max Act: 4.3087. Min Act: -0.0001

Data Index: 219812 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 4.9954. Min Range: -4.9954

Max Act: 3.9967. Min Act: -0.0001

Data Index: 631255 (C4 (Web Text))

Max Activating Token Index: 817