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

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

Neuron 3424 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.3033. Min Act: -0.0002

Data Index: 1103786 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.0078. Min Act: -0.0002

Data Index: 839973 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 1.3033. Min Range: -1.3033

Max Act: 0.8917. Min Act: -0.0002

Data Index: 734201 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 1.3033. Min Range: -1.3033

Max Act: 0.9422. Min Act: -0.0002

Data Index: 768257 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 1.3033. Min Range: -1.3033

Max Act: 0.7160. Min Act: -0.0002

Data Index: 606642 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.0365. Min Act: -0.0002

Data Index: 670910 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 1.3033. Min Range: -1.3033

Max Act: 0.6591. Min Act: -0.0002

Data Index: 1142389 (C4 (Web Text))

Max Activating Token Index: 668

Text #7

Max Range: 1.3033. Min Range: -1.3033

Max Act: 0.6915. Min Act: -0.0002

Data Index: 1096460 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 1.3033. Min Range: -1.3033

Max Act: 0.8111. Min Act: -0.0002

Data Index: 1061371 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 1.3033. Min Range: -1.3033

Max Act: 0.7891. Min Act: -0.0002

Data Index: 1064435 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 1.3033. Min Range: -1.3033

Max Act: 0.7342. Min Act: -0.0002

Data Index: 561850 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 1.3033. Min Range: -1.3033

Max Act: 0.7815. Min Act: -0.0002

Data Index: 1011665 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 1.3033. Min Range: -1.3033

Max Act: 0.8225. Min Act: -0.0002

Data Index: 906546 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 1.3033. Min Range: -1.3033

Max Act: 0.7418. Min Act: -0.0002

Data Index: 225651 (C4 (Web Text))

Max Activating Token Index: 619

Text #14

Max Range: 1.3033. Min Range: -1.3033

Max Act: 0.8067. Min Act: -0.0002

Data Index: 769185 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 1.3033. Min Range: -1.3033

Max Act: 0.6427. Min Act: -0.0002

Data Index: 1118336 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 1.3033. Min Range: -1.3033

Max Act: 0.8113. Min Act: -0.0002

Data Index: 1170863 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 1.3033. Min Range: -1.3033

Max Act: 0.7362. Min Act: -0.0002

Data Index: 899289 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 1.3033. Min Range: -1.3033

Max Act: 0.8086. Min Act: -0.0002

Data Index: 694923 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 1.3033. Min Range: -1.3033

Max Act: 0.7321. Min Act: -0.0002

Data Index: 1084175 (C4 (Web Text))

Max Activating Token Index: 356