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

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

Neuron 5003 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0977. Min Range: -2.0977

Max Act: 2.0977. Min Act: -0.0000

Data Index: 519868 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 2.0977. Min Range: -2.0977

Max Act: 1.9364. Min Act: -0.0000

Data Index: 151209 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 2.0977. Min Range: -2.0977

Max Act: 1.6595. Min Act: -0.0001

Data Index: 259834 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 2.0977. Min Range: -2.0977

Max Act: 1.8631. Min Act: -0.0000

Data Index: 206283 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 2.0977. Min Range: -2.0977

Max Act: 1.7969. Min Act: -0.0000

Data Index: 805043 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 2.0977. Min Range: -2.0977

Max Act: 1.7930. Min Act: -0.0000

Data Index: 1169667 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 2.0977. Min Range: -2.0977

Max Act: 1.5545. Min Act: -0.0000

Data Index: 49546 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 2.0977. Min Range: -2.0977

Max Act: 1.7276. Min Act: -0.0000

Data Index: 788052 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 2.0977. Min Range: -2.0977

Max Act: 1.8022. Min Act: -0.0000

Data Index: 585823 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 2.0977. Min Range: -2.0977

Max Act: 1.6670. Min Act: -0.0000

Data Index: 667357 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 2.0977. Min Range: -2.0977

Max Act: 1.6380. Min Act: -0.0000

Data Index: 398621 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 2.0977. Min Range: -2.0977

Max Act: 1.7186. Min Act: -0.0000

Data Index: 884165 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 2.0977. Min Range: -2.0977

Max Act: 1.6043. Min Act: -0.0000

Data Index: 1273269 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 2.0977. Min Range: -2.0977

Max Act: 1.4489. Min Act: -0.0000

Data Index: 1280838 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 2.0977. Min Range: -2.0977

Max Act: 1.5089. Min Act: -0.0000

Data Index: 622443 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 2.0977. Min Range: -2.0977

Max Act: 1.4216. Min Act: -0.0000

Data Index: 565060 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 2.0977. Min Range: -2.0977

Max Act: 1.3316. Min Act: -0.0000

Data Index: 994705 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 2.0977. Min Range: -2.0977

Max Act: 1.4878. Min Act: -0.0000

Data Index: 1251743 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 2.0977. Min Range: -2.0977

Max Act: 1.4715. Min Act: -0.0000

Data Index: 647964 (C4 (Web Text))

Max Activating Token Index: 821

Text #19

Max Range: 2.0977. Min Range: -2.0977

Max Act: 1.4247. Min Act: -0.0000

Data Index: 374565 (C4 (Web Text))

Max Activating Token Index: 724