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

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

Neuron 5344 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9481. Min Range: -2.9481

Max Act: 2.9481. Min Act: -0.0000

Data Index: 223412 (C4 (Web Text))

Max Activating Token Index: 698

Text #1

Max Range: 2.9481. Min Range: -2.9481

Max Act: 2.4044. Min Act: -0.0000

Data Index: 1114582 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 2.9481. Min Range: -2.9481

Max Act: 2.5332. Min Act: -0.0000

Data Index: 1144207 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 2.9481. Min Range: -2.9481

Max Act: 2.0460. Min Act: -0.0000

Data Index: 934990 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 2.9481. Min Range: -2.9481

Max Act: 2.1013. Min Act: -0.0000

Data Index: 855337 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 2.9481. Min Range: -2.9481

Max Act: 2.0296. Min Act: -0.0000

Data Index: 1122724 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 2.9481. Min Range: -2.9481

Max Act: 1.8555. Min Act: -0.0000

Data Index: 290742 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 2.9481. Min Range: -2.9481

Max Act: 1.7817. Min Act: -0.0000

Data Index: 499822 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 2.9481. Min Range: -2.9481

Max Act: 1.7680. Min Act: -0.0000

Data Index: 1229231 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 2.9481. Min Range: -2.9481

Max Act: 1.8398. Min Act: -0.0000

Data Index: 1085662 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 2.9481. Min Range: -2.9481

Max Act: 1.7685. Min Act: -0.0000

Data Index: 1110172 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 2.9481. Min Range: -2.9481

Max Act: 1.7237. Min Act: -0.0000

Data Index: 706307 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 2.9481. Min Range: -2.9481

Max Act: 1.8177. Min Act: -0.0000

Data Index: 846876 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 2.9481. Min Range: -2.9481

Max Act: 1.5492. Min Act: -0.0000

Data Index: 1109658 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 2.9481. Min Range: -2.9481

Max Act: 1.6626. Min Act: -0.0000

Data Index: 698041 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 2.9481. Min Range: -2.9481

Max Act: 1.6376. Min Act: -0.0000

Data Index: 486946 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 2.9481. Min Range: -2.9481

Max Act: 1.5703. Min Act: -0.0000

Data Index: 295462 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 2.9481. Min Range: -2.9481

Max Act: 1.5375. Min Act: -0.0000

Data Index: 515522 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 2.9481. Min Range: -2.9481

Max Act: 1.5185. Min Act: -0.0000

Data Index: 1170173 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 2.9481. Min Range: -2.9481

Max Act: 1.6218. Min Act: -0.0000

Data Index: 360515 (C4 (Web Text))

Max Activating Token Index: 516