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

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

Neuron 3275 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0431. Min Act: -0.0002

Data Index: 596194 (C4 (Web Text))

Max Activating Token Index: 434

Text #1

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0420. Min Act: -0.0003

Data Index: 602396 (C4 (Web Text))

Max Activating Token Index: 482

Text #2

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0418. Min Act: -0.0003

Data Index: 473175 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0410. Min Act: -0.0003

Data Index: 61946 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0405. Min Act: -0.0003

Data Index: 751209 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0412. Min Act: -0.0003

Data Index: 13591 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0404. Min Act: -0.0003

Data Index: 1277634 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0408. Min Act: -0.0002

Data Index: 795452 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0399. Min Act: -0.0003

Data Index: 1355921 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0402. Min Act: -0.0002

Data Index: 1311947 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0402. Min Act: -0.0002

Data Index: 508797 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0394. Min Act: -0.0003

Data Index: 1120578 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0397. Min Act: -0.0003

Data Index: 114147 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0388. Min Act: -0.0002

Data Index: 256653 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0395. Min Act: -0.0003

Data Index: 201775 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0395. Min Act: -0.0003

Data Index: 655365 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0391. Min Act: -0.0002

Data Index: 672533 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0378. Min Act: -0.0003

Data Index: 729736 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0385. Min Act: -0.0001

Data Index: 1169656 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0378. Min Act: -0.0002

Data Index: 792409 (C4 (Web Text))

Max Activating Token Index: 374