Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1703 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.5461. Min Act: -0.0000

Data Index: 890304 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4459. Min Act: -0.0001

Data Index: 229907 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.3996. Min Act: -0.0001

Data Index: 485135 (C4 (Web Text))

Max Activating Token Index: 497

Text #3

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4004. Min Act: -0.0001

Data Index: 695475 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.3771. Min Act: -0.0001

Data Index: 493911 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.3716. Min Act: -0.0001

Data Index: 1240706 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.3832. Min Act: -0.0001

Data Index: 494617 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.3670. Min Act: -0.0001

Data Index: 1225029 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.3508. Min Act: -0.0001

Data Index: 650068 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.3590. Min Act: -0.0000

Data Index: 941531 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.3567. Min Act: -0.0001

Data Index: 866455 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.3538. Min Act: -0.0000

Data Index: 225185 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.3528. Min Act: -0.0000

Data Index: 212965 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.3646. Min Act: -0.0001

Data Index: 951672 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.3508. Min Act: -0.0001

Data Index: 1252609 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.3510. Min Act: -0.0001

Data Index: 342118 (C4 (Web Text))

Max Activating Token Index: 1001

Text #16

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.3145. Min Act: -0.0001

Data Index: 359883 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.3444. Min Act: -0.0001

Data Index: 20383 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.3331. Min Act: -0.0001

Data Index: 1118454 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.3077. Min Act: -0.0001

Data Index: 1126132 (C4 (Web Text))

Max Activating Token Index: 663