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

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

Neuron 107 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.5840. Min Act: -0.0000

Data Index: 86009 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.5690. Min Act: -0.0000

Data Index: 1171417 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.5406. Min Act: -0.0000

Data Index: 870680 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4900. Min Act: -0.0000

Data Index: 504998 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4958. Min Act: -0.0000

Data Index: 1008051 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.5423. Min Act: -0.0000

Data Index: 1284929 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4987. Min Act: -0.0000

Data Index: 120801 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4609. Min Act: -0.0000

Data Index: 78532 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4123. Min Act: -0.0000

Data Index: 629338 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4469. Min Act: -0.0000

Data Index: 558106 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4763. Min Act: -0.0000

Data Index: 820066 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4389. Min Act: -0.0000

Data Index: 402427 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4356. Min Act: -0.0000

Data Index: 1054413 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4704. Min Act: -0.0000

Data Index: 1293732 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4375. Min Act: -0.0000

Data Index: 280490 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.3782. Min Act: -0.0000

Data Index: 927437 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4591. Min Act: -0.0000

Data Index: 1295412 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4005. Min Act: -0.0000

Data Index: 81189 (C4 (Web Text))

Max Activating Token Index: 388

Text #18

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4144. Min Act: -0.0000

Data Index: 736045 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.3944. Min Act: -0.0000

Data Index: 1627933 (Python Code)

Max Activating Token Index: 756