Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1510 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9429. Min Range: -1.9429

Max Act: 1.9429. Min Act: -0.0000

Data Index: 563503 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 1.9429. Min Range: -1.9429

Max Act: 1.5097. Min Act: -0.0000

Data Index: 913121 (C4 (Web Text))

Max Activating Token Index: 879

Text #2

Max Range: 1.9429. Min Range: -1.9429

Max Act: 1.3331. Min Act: -0.0000

Data Index: 279007 (C4 (Web Text))

Max Activating Token Index: 341

Text #3

Max Range: 1.9429. Min Range: -1.9429

Max Act: 1.0232. Min Act: -0.0000

Data Index: 283142 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 1.9429. Min Range: -1.9429

Max Act: 1.0416. Min Act: -0.0000

Data Index: 378928 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 1.9429. Min Range: -1.9429

Max Act: 0.8989. Min Act: -0.0000

Data Index: 1069436 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 1.9429. Min Range: -1.9429

Max Act: 0.8327. Min Act: -0.0000

Data Index: 980653 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 1.9429. Min Range: -1.9429

Max Act: 0.8351. Min Act: -0.0000

Data Index: 1356730 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 1.9429. Min Range: -1.9429

Max Act: 0.8807. Min Act: -0.0000

Data Index: 651949 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 1.9429. Min Range: -1.9429

Max Act: 0.7960. Min Act: -0.0000

Data Index: 296006 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 1.9429. Min Range: -1.9429

Max Act: 0.7059. Min Act: -0.0000

Data Index: 518085 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 1.9429. Min Range: -1.9429

Max Act: 0.6869. Min Act: -0.0000

Data Index: 1352877 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 1.9429. Min Range: -1.9429

Max Act: 0.8670. Min Act: -0.0000

Data Index: 411589 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 1.9429. Min Range: -1.9429

Max Act: 0.7834. Min Act: -0.0000

Data Index: 591576 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 1.9429. Min Range: -1.9429

Max Act: 0.7202. Min Act: -0.0000

Data Index: 974187 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 1.9429. Min Range: -1.9429

Max Act: 0.7409. Min Act: -0.0000

Data Index: 799132 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 1.9429. Min Range: -1.9429

Max Act: 0.6156. Min Act: -0.0000

Data Index: 433004 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 1.9429. Min Range: -1.9429

Max Act: 0.6687. Min Act: -0.0000

Data Index: 1223071 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 1.9429. Min Range: -1.9429

Max Act: 0.6847. Min Act: -0.0000

Data Index: 194191 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 1.9429. Min Range: -1.9429

Max Act: 0.5766. Min Act: -0.0000

Data Index: 686936 (C4 (Web Text))

Max Activating Token Index: 773