Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 559 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0494. Min Act: -0.0003

Data Index: 210831 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1292418 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0449. Min Act: -0.0003

Data Index: 646684 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0443. Min Act: -0.0003

Data Index: 541921 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0442. Min Act: -0.0003

Data Index: 1169958 (C4 (Web Text))

Max Activating Token Index: 565

Text #5

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0423. Min Act: -0.0003

Data Index: 1060204 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0412. Min Act: -0.0003

Data Index: 602719 (C4 (Web Text))

Max Activating Token Index: 774

Text #7

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0394. Min Act: -0.0003

Data Index: 1341639 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0403. Min Act: -0.0004

Data Index: 207669 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0400. Min Act: -0.0004

Data Index: 387376 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0397. Min Act: -0.0003

Data Index: 1190453 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0400. Min Act: -0.0003

Data Index: 1012864 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0409. Min Act: -0.0003

Data Index: 1036410 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0393. Min Act: -0.0003

Data Index: 817428 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0385. Min Act: -0.0003

Data Index: 1181396 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0383. Min Act: -0.0003

Data Index: 369435 (C4 (Web Text))

Max Activating Token Index: 248

Text #16

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0393. Min Act: -0.0003

Data Index: 872502 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0388. Min Act: -0.0003

Data Index: 132969 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0391. Min Act: -0.0003

Data Index: 567318 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0376. Min Act: -0.0003

Data Index: 1289302 (C4 (Web Text))

Max Activating Token Index: 925