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

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

Neuron 1074 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.7570. Min Act: -0.0000

Data Index: 302299 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.7563. Min Act: -0.0000

Data Index: 176203 (C4 (Web Text))

Max Activating Token Index: 225

Text #2

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.7439. Min Act: 0.0000

Data Index: 459855 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.6901. Min Act: -0.0000

Data Index: 1288369 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.7222. Min Act: -0.0000

Data Index: 352952 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.7126. Min Act: -0.0000

Data Index: 767598 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.7016. Min Act: -0.0000

Data Index: 235406 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.6861. Min Act: -0.0000

Data Index: 403358 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.6606. Min Act: 0.0000

Data Index: 574520 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.6246. Min Act: -0.0000

Data Index: 152806 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.6615. Min Act: -0.0000

Data Index: 193707 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.6218. Min Act: -0.0000

Data Index: 451859 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.6574. Min Act: -0.0000

Data Index: 1091286 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.6030. Min Act: -0.0000

Data Index: 397350 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.6089. Min Act: -0.0000

Data Index: 411983 (C4 (Web Text))

Max Activating Token Index: 618

Text #15

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.5662. Min Act: -0.0000

Data Index: 635403 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.5837. Min Act: -0.0000

Data Index: 154889 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.5874. Min Act: 0.0000

Data Index: 90835 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.6225. Min Act: -0.0000

Data Index: 345581 (C4 (Web Text))

Max Activating Token Index: 740

Text #19

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.5824. Min Act: -0.0000

Data Index: 533790 (C4 (Web Text))

Max Activating Token Index: 716