Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4254 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0503. Min Act: -0.0002

Data Index: 1018989 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0315. Min Act: -0.0002

Data Index: 848286 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0433. Min Act: -0.0002

Data Index: 207894 (C4 (Web Text))

Max Activating Token Index: 635

Text #3

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0373. Min Act: -0.0002

Data Index: 1106302 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0449. Min Act: -0.0002

Data Index: 1062693 (C4 (Web Text))

Max Activating Token Index: 357

Text #5

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0396. Min Act: -0.0002

Data Index: 1163323 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0293. Min Act: -0.0002

Data Index: 923933 (C4 (Web Text))

Max Activating Token Index: 794

Text #7

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0415. Min Act: -0.0002

Data Index: 1329415 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0438. Min Act: -0.0002

Data Index: 729947 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0410. Min Act: -0.0002

Data Index: 953841 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0400. Min Act: -0.0002

Data Index: 701698 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0359. Min Act: -0.0002

Data Index: 571468 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0381. Min Act: -0.0002

Data Index: 30808 (C4 (Web Text))

Max Activating Token Index: 598

Text #13

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0409. Min Act: -0.0002

Data Index: 628481 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0425. Min Act: -0.0002

Data Index: 1191253 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0389. Min Act: -0.0002

Data Index: 468636 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0340. Min Act: -0.0002

Data Index: 867549 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0351. Min Act: -0.0002

Data Index: 1156693 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0338. Min Act: -0.0002

Data Index: 724654 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0314. Min Act: -0.0002

Data Index: 1119678 (C4 (Web Text))

Max Activating Token Index: 300