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

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

Neuron 428 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1731. Min Range: -1.1731

Max Act: 1.1731. Min Act: -0.0001

Data Index: 451948 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.9818. Min Act: -0.0000

Data Index: 5996 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.9424. Min Act: -0.0001

Data Index: 1067485 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.8875. Min Act: -0.0000

Data Index: 1302655 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.8375. Min Act: -0.0001

Data Index: 220595 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.8732. Min Act: -0.0000

Data Index: 348100 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.8854. Min Act: -0.0000

Data Index: 1277012 (C4 (Web Text))

Max Activating Token Index: 246

Text #7

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.7657. Min Act: -0.0000

Data Index: 18354 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.8372. Min Act: -0.0000

Data Index: 413945 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.8130. Min Act: -0.0001

Data Index: 906454 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.7852. Min Act: -0.0000

Data Index: 470391 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.8817. Min Act: -0.0000

Data Index: 429596 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.8370. Min Act: -0.0000

Data Index: 324528 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.9261. Min Act: -0.0000

Data Index: 622037 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.8547. Min Act: -0.0000

Data Index: 765946 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.7668. Min Act: -0.0000

Data Index: 1978 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.8004. Min Act: -0.0000

Data Index: 614052 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.7954. Min Act: -0.0000

Data Index: 1251065 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.7911. Min Act: -0.0000

Data Index: 532514 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.7404. Min Act: -0.0000

Data Index: 743311 (C4 (Web Text))

Max Activating Token Index: 78