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

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

Neuron 3301 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.6455. Min Act: -0.0001

Data Index: 305850 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.5717. Min Act: -0.0000

Data Index: 394283 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.4557. Min Act: -0.0001

Data Index: 1202824 (C4 (Web Text))

Max Activating Token Index: 661

Text #3

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.4266. Min Act: -0.0000

Data Index: 321166 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.5710. Min Act: -0.0001

Data Index: 22467 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.2803. Min Act: -0.0000

Data Index: 1338241 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.2945. Min Act: -0.0001

Data Index: 10782 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.3089. Min Act: -0.0000

Data Index: 508490 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.3063. Min Act: -0.0001

Data Index: 446093 (C4 (Web Text))

Max Activating Token Index: 872

Text #9

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.2067. Min Act: -0.0001

Data Index: 966880 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.1636. Min Act: -0.0001

Data Index: 829925 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.1402. Min Act: -0.0001

Data Index: 579893 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.1650. Min Act: -0.0000

Data Index: 862131 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.1615. Min Act: -0.0001

Data Index: 287102 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.0788. Min Act: -0.0001

Data Index: 442284 (C4 (Web Text))

Max Activating Token Index: 415

Text #15

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.2590. Min Act: -0.0000

Data Index: 950857 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.0870. Min Act: -0.0001

Data Index: 1026891 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.0615. Min Act: -0.0001

Data Index: 244679 (C4 (Web Text))

Max Activating Token Index: 503

Text #18

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.0408. Min Act: -0.0000

Data Index: 630630 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.0386. Min Act: -0.0000

Data Index: 198687 (C4 (Web Text))

Max Activating Token Index: 949