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

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

Neuron 2547 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.7342. Min Act: -0.0000

Data Index: 11346 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.7759. Min Act: -0.0000

Data Index: 1119253 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.7826. Min Act: -0.0000

Data Index: 224356 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.7272. Min Act: -0.0000

Data Index: 102401 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.6789. Min Act: -0.0000

Data Index: 616015 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.6932. Min Act: -0.0000

Data Index: 1316541 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.6646. Min Act: -0.0000

Data Index: 694768 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.6541. Min Act: -0.0000

Data Index: 1193113 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.6334. Min Act: -0.0000

Data Index: 561264 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.6411. Min Act: -0.0000

Data Index: 22238 (C4 (Web Text))

Max Activating Token Index: 968

Text #10

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.4262. Min Act: -0.0000

Data Index: 928217 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.4288. Min Act: -0.0000

Data Index: 371975 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.4120. Min Act: -0.0000

Data Index: 637935 (C4 (Web Text))

Max Activating Token Index: 436

Text #13

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.4095. Min Act: -0.0000

Data Index: 403939 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.4044. Min Act: -0.0000

Data Index: 1046261 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.4005. Min Act: -0.0000

Data Index: 1008582 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.3677. Min Act: -0.0000

Data Index: 607803 (C4 (Web Text))

Max Activating Token Index: 416

Text #17

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.3756. Min Act: -0.0000

Data Index: 1266010 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.3390. Min Act: -0.0000

Data Index: 1009737 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.3608. Min Act: -0.0000

Data Index: 554538 (C4 (Web Text))

Max Activating Token Index: 587