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

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

Neuron 1542 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0391. Min Act: -0.0004

Data Index: 1191665 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0370. Min Act: -0.0004

Data Index: 464499 (C4 (Web Text))

Max Activating Token Index: 614

Text #2

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0353. Min Act: -0.0004

Data Index: 1262791 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0332. Min Act: -0.0004

Data Index: 794400 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0349. Min Act: -0.0004

Data Index: 699670 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0360. Min Act: -0.0004

Data Index: 271266 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0348. Min Act: -0.0004

Data Index: 899429 (C4 (Web Text))

Max Activating Token Index: 529

Text #7

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0316. Min Act: -0.0004

Data Index: 1134100 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0329. Min Act: -0.0004

Data Index: 688680 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0310. Min Act: -0.0004

Data Index: 909913 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0343. Min Act: -0.0004

Data Index: 1346591 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0343. Min Act: -0.0004

Data Index: 832719 (C4 (Web Text))

Max Activating Token Index: 882

Text #12

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0323. Min Act: -0.0004

Data Index: 709841 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0333. Min Act: -0.0004

Data Index: 1075975 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0319. Min Act: -0.0004

Data Index: 330959 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0336. Min Act: -0.0004

Data Index: 147641 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0324. Min Act: -0.0004

Data Index: 1275967 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0305. Min Act: -0.0004

Data Index: 1245298 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0334. Min Act: -0.0004

Data Index: 1328910 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0310. Min Act: -0.0004

Data Index: 1277012 (C4 (Web Text))

Max Activating Token Index: 280