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

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

Neuron 1497 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0327. Min Act: -0.0003

Data Index: 113735 (C4 (Web Text))

Max Activating Token Index: 543

Text #1

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0326. Min Act: -0.0003

Data Index: 1292745 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0333. Min Act: -0.0003

Data Index: 457982 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0301. Min Act: -0.0003

Data Index: 1162336 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0295. Min Act: -0.0003

Data Index: 931059 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0283. Min Act: -0.0003

Data Index: 835564 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0284. Min Act: -0.0003

Data Index: 160539 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0292. Min Act: -0.0003

Data Index: 716909 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0287. Min Act: -0.0003

Data Index: 349563 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0276. Min Act: -0.0003

Data Index: 415135 (C4 (Web Text))

Max Activating Token Index: 781

Text #10

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0295. Min Act: -0.0003

Data Index: 1114429 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0283. Min Act: -0.0003

Data Index: 865465 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0294. Min Act: -0.0003

Data Index: 794603 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0274. Min Act: -0.0003

Data Index: 690165 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0250. Min Act: -0.0003

Data Index: 1209326 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0283. Min Act: -0.0003

Data Index: 175498 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0266. Min Act: -0.0003

Data Index: 1090765 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0255. Min Act: -0.0003

Data Index: 1166516 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0258. Min Act: -0.0003

Data Index: 1306952 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0276. Min Act: -0.0003

Data Index: 664390 (C4 (Web Text))

Max Activating Token Index: 461