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

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

Neuron 711 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8697. Min Act: -0.0001

Data Index: 1065427 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8177. Min Act: -0.0001

Data Index: 989075 (C4 (Web Text))

Max Activating Token Index: 865

Text #2

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7715. Min Act: -0.0001

Data Index: 835551 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7303. Min Act: -0.0001

Data Index: 95735 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7212. Min Act: -0.0001

Data Index: 266295 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7337. Min Act: -0.0001

Data Index: 359094 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6894. Min Act: -0.0001

Data Index: 675250 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6885. Min Act: -0.0001

Data Index: 1058902 (C4 (Web Text))

Max Activating Token Index: 646

Text #8

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6704. Min Act: -0.0001

Data Index: 751684 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6508. Min Act: -0.0001

Data Index: 351687 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6437. Min Act: -0.0001

Data Index: 1264672 (C4 (Web Text))

Max Activating Token Index: 794

Text #11

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6665. Min Act: -0.0001

Data Index: 1303033 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6426. Min Act: -0.0001

Data Index: 1226119 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6419. Min Act: -0.0001

Data Index: 635123 (C4 (Web Text))

Max Activating Token Index: 795

Text #14

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6313. Min Act: -0.0001

Data Index: 248178 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6277. Min Act: -0.0001

Data Index: 572533 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6653. Min Act: -0.0001

Data Index: 674222 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6305. Min Act: -0.0001

Data Index: 1122614 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6215. Min Act: -0.0001

Data Index: 1196772 (C4 (Web Text))

Max Activating Token Index: 716

Text #19

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.5621. Min Act: -0.0001

Data Index: 576717 (C4 (Web Text))

Max Activating Token Index: 649