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

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

Neuron 3501 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: 1.0893. Min Range: -1.0893

Max Act: 1.0893. Min Act: -0.0000

Data Index: 88033 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.8499. Min Act: -0.0001

Data Index: 925181 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.8733. Min Act: -0.0001

Data Index: 364179 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.7818. Min Act: -0.0000

Data Index: 72863 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.7408. Min Act: -0.0000

Data Index: 77780 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.6969. Min Act: -0.0000

Data Index: 498860 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.7130. Min Act: -0.0000

Data Index: 44028 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.7169. Min Act: -0.0000

Data Index: 799598 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.6829. Min Act: -0.0000

Data Index: 491781 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.6550. Min Act: -0.0000

Data Index: 488889 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.6846. Min Act: -0.0000

Data Index: 163697 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.6743. Min Act: -0.0000

Data Index: 972168 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.7654. Min Act: -0.0000

Data Index: 489775 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.7017. Min Act: -0.0000

Data Index: 254209 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.6404. Min Act: -0.0001

Data Index: 795891 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.6325. Min Act: -0.0001

Data Index: 222356 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.6472. Min Act: -0.0000

Data Index: 89884 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.6299. Min Act: -0.0000

Data Index: 1229479 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.5938. Min Act: -0.0000

Data Index: 369806 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.6111. Min Act: -0.0000

Data Index: 613225 (C4 (Web Text))

Max Activating Token Index: 410