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

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

Neuron 1916 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: 1.0627. Min Range: -1.0627

Max Act: 1.0580. Min Act: -0.0001

Data Index: 29079 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 1.0627. Min Range: -1.0627

Max Act: 1.0627. Min Act: -0.0001

Data Index: 1035551 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 1.0627. Min Range: -1.0627

Max Act: 0.9728. Min Act: -0.0000

Data Index: 79625 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 1.0627. Min Range: -1.0627

Max Act: 0.8990. Min Act: -0.0001

Data Index: 376365 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 1.0627. Min Range: -1.0627

Max Act: 0.8783. Min Act: -0.0001

Data Index: 1280523 (C4 (Web Text))

Max Activating Token Index: 696

Text #5

Max Range: 1.0627. Min Range: -1.0627

Max Act: 0.7905. Min Act: -0.0001

Data Index: 196478 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 1.0627. Min Range: -1.0627

Max Act: 0.8482. Min Act: -0.0000

Data Index: 1349708 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 1.0627. Min Range: -1.0627

Max Act: 0.7653. Min Act: -0.0001

Data Index: 943048 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 1.0627. Min Range: -1.0627

Max Act: 0.8201. Min Act: -0.0000

Data Index: 1436172 (Python Code)

Max Activating Token Index: 979

Text #9

Max Range: 1.0627. Min Range: -1.0627

Max Act: 0.8092. Min Act: -0.0001

Data Index: 171968 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 1.0627. Min Range: -1.0627

Max Act: 0.7845. Min Act: -0.0001

Data Index: 291185 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 1.0627. Min Range: -1.0627

Max Act: 0.8127. Min Act: -0.0001

Data Index: 338631 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 1.0627. Min Range: -1.0627

Max Act: 0.6992. Min Act: -0.0001

Data Index: 980177 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 1.0627. Min Range: -1.0627

Max Act: 0.8818. Min Act: -0.0000

Data Index: 1587263 (Python Code)

Max Activating Token Index: 804

Text #14

Max Range: 1.0627. Min Range: -1.0627

Max Act: 0.7944. Min Act: -0.0000

Data Index: 480211 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 1.0627. Min Range: -1.0627

Max Act: 0.8181. Min Act: -0.0001

Data Index: 1037963 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 1.0627. Min Range: -1.0627

Max Act: 0.7860. Min Act: -0.0000

Data Index: 1637111 (Python Code)

Max Activating Token Index: 614

Text #17

Max Range: 1.0627. Min Range: -1.0627

Max Act: 0.8128. Min Act: -0.0001

Data Index: 33396 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 1.0627. Min Range: -1.0627

Max Act: 0.8128. Min Act: -0.0001

Data Index: 653772 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 1.0627. Min Range: -1.0627

Max Act: 0.8390. Min Act: -0.0000

Data Index: 1213507 (C4 (Web Text))

Max Activating Token Index: 570