Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1994 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0550. Min Act: -0.0006

Data Index: 138283 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0552. Min Act: -0.0006

Data Index: 655401 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0511. Min Act: -0.0006

Data Index: 1057041 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0511. Min Act: -0.0006

Data Index: 434772 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0530. Min Act: -0.0006

Data Index: 227380 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0475. Min Act: -0.0006

Data Index: 543751 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0508. Min Act: -0.0006

Data Index: 744279 (C4 (Web Text))

Max Activating Token Index: 508

Text #7

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0520. Min Act: -0.0006

Data Index: 729522 (C4 (Web Text))

Max Activating Token Index: 989

Text #8

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0489. Min Act: -0.0006

Data Index: 1037286 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0476. Min Act: -0.0006

Data Index: 564925 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0483. Min Act: -0.0006

Data Index: 934164 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0480. Min Act: -0.0006

Data Index: 366702 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0481. Min Act: -0.0006

Data Index: 119881 (C4 (Web Text))

Max Activating Token Index: 198

Text #13

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0466. Min Act: -0.0006

Data Index: 2532 (C4 (Web Text))

Max Activating Token Index: 491

Text #14

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0460. Min Act: -0.0006

Data Index: 422543 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0451. Min Act: -0.0006

Data Index: 854442 (C4 (Web Text))

Max Activating Token Index: 199

Text #16

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0478. Min Act: -0.0006

Data Index: 118896 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0437. Min Act: -0.0006

Data Index: 287225 (C4 (Web Text))

Max Activating Token Index: 1014

Text #18

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0490. Min Act: -0.0006

Data Index: 365993 (C4 (Web Text))

Max Activating Token Index: 679

Text #19

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0449. Min Act: -0.0006

Data Index: 55442 (C4 (Web Text))

Max Activating Token Index: 621