Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1783 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.9228. Min Act: -0.0003

Data Index: 74108 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.8834. Min Act: -0.0003

Data Index: 174200 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.8686. Min Act: -0.0003

Data Index: 834892 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.8780. Min Act: -0.0003

Data Index: 149679 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.8568. Min Act: -0.0003

Data Index: 220247 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.8248. Min Act: -0.0003

Data Index: 126896 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.8527. Min Act: -0.0003

Data Index: 850289 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.8255. Min Act: -0.0003

Data Index: 1215622 (C4 (Web Text))

Max Activating Token Index: 997

Text #8

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.7958. Min Act: -0.0003

Data Index: 1161517 (C4 (Web Text))

Max Activating Token Index: 828

Text #9

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.8399. Min Act: -0.0003

Data Index: 425555 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.8706. Min Act: -0.0003

Data Index: 1313448 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.8401. Min Act: -0.0003

Data Index: 898313 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.8349. Min Act: -0.0003

Data Index: 882539 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.8301. Min Act: -0.0003

Data Index: 731112 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.8048. Min Act: -0.0003

Data Index: 497309 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.7807. Min Act: -0.0003

Data Index: 242816 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.8064. Min Act: -0.0003

Data Index: 1164077 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.8850. Min Act: -0.0003

Data Index: 305792 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.8589. Min Act: -0.0003

Data Index: 369868 (C4 (Web Text))

Max Activating Token Index: 911

Text #19

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.7629. Min Act: -0.0003

Data Index: 465250 (C4 (Web Text))

Max Activating Token Index: 304