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

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

Neuron 612 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0911. Min Range: -1.0911

Max Act: 1.0911. Min Act: -0.0000

Data Index: 116595 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 1.0911. Min Range: -1.0911

Max Act: 1.0695. Min Act: -0.0000

Data Index: 631085 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 1.0911. Min Range: -1.0911

Max Act: 0.9379. Min Act: -0.0000

Data Index: 460124 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 1.0911. Min Range: -1.0911

Max Act: 0.8943. Min Act: -0.0000

Data Index: 1119195 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 1.0911. Min Range: -1.0911

Max Act: 0.9302. Min Act: -0.0000

Data Index: 538001 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 1.0911. Min Range: -1.0911

Max Act: 0.9016. Min Act: -0.0000

Data Index: 54217 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 1.0911. Min Range: -1.0911

Max Act: 0.8939. Min Act: -0.0000

Data Index: 1262245 (C4 (Web Text))

Max Activating Token Index: 376

Text #7

Max Range: 1.0911. Min Range: -1.0911

Max Act: 0.8607. Min Act: -0.0000

Data Index: 1635 (C4 (Web Text))

Max Activating Token Index: 991

Text #8

Max Range: 1.0911. Min Range: -1.0911

Max Act: 0.8301. Min Act: -0.0000

Data Index: 162166 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 1.0911. Min Range: -1.0911

Max Act: 0.8875. Min Act: -0.0000

Data Index: 634572 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 1.0911. Min Range: -1.0911

Max Act: 0.9214. Min Act: -0.0000

Data Index: 778303 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 1.0911. Min Range: -1.0911

Max Act: 0.8541. Min Act: -0.0000

Data Index: 1048346 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 1.0911. Min Range: -1.0911

Max Act: 0.8305. Min Act: -0.0000

Data Index: 350943 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 1.0911. Min Range: -1.0911

Max Act: 0.8489. Min Act: -0.0000

Data Index: 793344 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 1.0911. Min Range: -1.0911

Max Act: 0.8026. Min Act: -0.0000

Data Index: 995850 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 1.0911. Min Range: -1.0911

Max Act: 0.8250. Min Act: -0.0000

Data Index: 669887 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 1.0911. Min Range: -1.0911

Max Act: 0.8329. Min Act: -0.0000

Data Index: 1080233 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 1.0911. Min Range: -1.0911

Max Act: 0.8888. Min Act: -0.0000

Data Index: 570582 (C4 (Web Text))

Max Activating Token Index: 945

Text #18

Max Range: 1.0911. Min Range: -1.0911

Max Act: 0.8527. Min Act: -0.0000

Data Index: 306665 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 1.0911. Min Range: -1.0911

Max Act: 0.8241. Min Act: -0.0000

Data Index: 798623 (C4 (Web Text))

Max Activating Token Index: 143