Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2229 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.3245. Min Act: -0.0001

Data Index: 1168229 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.3228. Min Act: -0.0001

Data Index: 285814 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.3149. Min Act: -0.0001

Data Index: 378191 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.3030. Min Act: -0.0001

Data Index: 599309 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.3030. Min Act: -0.0001

Data Index: 910699 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.3030. Min Act: -0.0001

Data Index: 449552 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.3100. Min Act: -0.0001

Data Index: 454104 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2983. Min Act: -0.0001

Data Index: 171666 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2785. Min Act: -0.0001

Data Index: 1331213 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2845. Min Act: -0.0001

Data Index: 545580 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2732. Min Act: -0.0001

Data Index: 1206823 (C4 (Web Text))

Max Activating Token Index: 447

Text #11

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2605. Min Act: -0.0001

Data Index: 523353 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2698. Min Act: -0.0001

Data Index: 476571 (C4 (Web Text))

Max Activating Token Index: 446

Text #13

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2768. Min Act: -0.0001

Data Index: 29676 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2648. Min Act: -0.0001

Data Index: 654109 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2488. Min Act: -0.0001

Data Index: 306458 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2616. Min Act: -0.0001

Data Index: 1279213 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2601. Min Act: -0.0001

Data Index: 491918 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2606. Min Act: -0.0001

Data Index: 577960 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2575. Min Act: -0.0001

Data Index: 660575 (C4 (Web Text))

Max Activating Token Index: 915