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

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

Neuron 250 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0517. Min Act: -0.0001

Data Index: 683660 (C4 (Web Text))

Max Activating Token Index: 480

Text #1

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0437. Min Act: -0.0001

Data Index: 402303 (C4 (Web Text))

Max Activating Token Index: 385

Text #2

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0400. Min Act: -0.0001

Data Index: 453 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0357. Min Act: -0.0001

Data Index: 1303972 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0420. Min Act: -0.0001

Data Index: 651613 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0399. Min Act: -0.0001

Data Index: 814443 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1155868 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0418. Min Act: -0.0001

Data Index: 629341 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0414. Min Act: -0.0001

Data Index: 768941 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0409. Min Act: -0.0001

Data Index: 385439 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0430. Min Act: -0.0001

Data Index: 94125 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0377. Min Act: -0.0001

Data Index: 1205342 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0392. Min Act: -0.0001

Data Index: 255319 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0413. Min Act: -0.0001

Data Index: 53111 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0417. Min Act: -0.0001

Data Index: 355898 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0405. Min Act: -0.0001

Data Index: 1333840 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0400. Min Act: -0.0001

Data Index: 50764 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0393. Min Act: -0.0001

Data Index: 554810 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0393. Min Act: -0.0001

Data Index: 1153256 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0395. Min Act: -0.0002

Data Index: 839091 (C4 (Web Text))

Max Activating Token Index: 285