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

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

Neuron 786 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7631. Min Range: -0.7631

Max Act: 0.7600. Min Act: -0.0000

Data Index: 540408 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 0.7631. Min Range: -0.7631

Max Act: 0.7278. Min Act: -0.0000

Data Index: 991983 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 0.7631. Min Range: -0.7631

Max Act: 0.7080. Min Act: -0.0000

Data Index: 722628 (C4 (Web Text))

Max Activating Token Index: 638

Text #3

Max Range: 0.7631. Min Range: -0.7631

Max Act: 0.7266. Min Act: -0.0000

Data Index: 1172082 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 0.7631. Min Range: -0.7631

Max Act: 0.6953. Min Act: -0.0000

Data Index: 694660 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 0.7631. Min Range: -0.7631

Max Act: 0.7631. Min Act: -0.0000

Data Index: 1349317 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 0.7631. Min Range: -0.7631

Max Act: 0.7439. Min Act: -0.0000

Data Index: 360635 (C4 (Web Text))

Max Activating Token Index: 493

Text #7

Max Range: 0.7631. Min Range: -0.7631

Max Act: 0.6997. Min Act: -0.0000

Data Index: 499088 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 0.7631. Min Range: -0.7631

Max Act: 0.6348. Min Act: -0.0000

Data Index: 227276 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 0.7631. Min Range: -0.7631

Max Act: 0.7090. Min Act: -0.0000

Data Index: 196768 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 0.7631. Min Range: -0.7631

Max Act: 0.6919. Min Act: -0.0000

Data Index: 277796 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 0.7631. Min Range: -0.7631

Max Act: 0.6858. Min Act: -0.0000

Data Index: 1086229 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 0.7631. Min Range: -0.7631

Max Act: 0.6649. Min Act: -0.0000

Data Index: 967741 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 0.7631. Min Range: -0.7631

Max Act: 0.6961. Min Act: -0.0000

Data Index: 73221 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 0.7631. Min Range: -0.7631

Max Act: 0.6657. Min Act: -0.0000

Data Index: 1094854 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 0.7631. Min Range: -0.7631

Max Act: 0.6607. Min Act: -0.0000

Data Index: 1297699 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 0.7631. Min Range: -0.7631

Max Act: 0.6100. Min Act: -0.0000

Data Index: 208351 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 0.7631. Min Range: -0.7631

Max Act: 0.6363. Min Act: -0.0000

Data Index: 748279 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 0.7631. Min Range: -0.7631

Max Act: 0.7084. Min Act: -0.0000

Data Index: 731099 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 0.7631. Min Range: -0.7631

Max Act: 0.6250. Min Act: -0.0000

Data Index: 1246760 (C4 (Web Text))

Max Activating Token Index: 597