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

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

Neuron 5765 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9826. Min Range: -1.9826

Max Act: 1.9826. Min Act: -0.0000

Data Index: 894523 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 1.9826. Min Range: -1.9826

Max Act: 1.8418. Min Act: -0.0000

Data Index: 888326 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 1.9826. Min Range: -1.9826

Max Act: 1.6750. Min Act: -0.0000

Data Index: 1124646 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 1.9826. Min Range: -1.9826

Max Act: 1.6318. Min Act: -0.0000

Data Index: 1187618 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 1.9826. Min Range: -1.9826

Max Act: 1.6683. Min Act: -0.0000

Data Index: 795036 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 1.9826. Min Range: -1.9826

Max Act: 1.6171. Min Act: -0.0000

Data Index: 1204606 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 1.9826. Min Range: -1.9826

Max Act: 1.4915. Min Act: -0.0000

Data Index: 562260 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 1.9826. Min Range: -1.9826

Max Act: 1.3982. Min Act: -0.0000

Data Index: 379336 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 1.9826. Min Range: -1.9826

Max Act: 1.2243. Min Act: -0.0000

Data Index: 10375 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 1.9826. Min Range: -1.9826

Max Act: 1.4389. Min Act: -0.0000

Data Index: 1173180 (C4 (Web Text))

Max Activating Token Index: 330

Text #10

Max Range: 1.9826. Min Range: -1.9826

Max Act: 1.3506. Min Act: -0.0000

Data Index: 446102 (C4 (Web Text))

Max Activating Token Index: 714

Text #11

Max Range: 1.9826. Min Range: -1.9826

Max Act: 1.3278. Min Act: -0.0000

Data Index: 643144 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 1.9826. Min Range: -1.9826

Max Act: 1.3868. Min Act: -0.0000

Data Index: 97048 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 1.9826. Min Range: -1.9826

Max Act: 1.4822. Min Act: -0.0000

Data Index: 377405 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 1.9826. Min Range: -1.9826

Max Act: 1.3676. Min Act: -0.0000

Data Index: 370630 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 1.9826. Min Range: -1.9826

Max Act: 1.3393. Min Act: 0.0000

Data Index: 721194 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 1.9826. Min Range: -1.9826

Max Act: 1.3419. Min Act: -0.0000

Data Index: 138020 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 1.9826. Min Range: -1.9826

Max Act: 1.2998. Min Act: -0.0000

Data Index: 29343 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 1.9826. Min Range: -1.9826

Max Act: 1.3338. Min Act: -0.0000

Data Index: 105898 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 1.9826. Min Range: -1.9826

Max Act: 1.3196. Min Act: -0.0000

Data Index: 280835 (C4 (Web Text))

Max Activating Token Index: 421