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

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

Neuron 3097 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.6756. Min Act: -0.0000

Data Index: 609625 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.5838. Min Act: -0.0000

Data Index: 903456 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.4020. Min Act: -0.0000

Data Index: 454500 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.5016. Min Act: -0.0000

Data Index: 697379 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.3790. Min Act: -0.0000

Data Index: 251618 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.3691. Min Act: -0.0000

Data Index: 347866 (C4 (Web Text))

Max Activating Token Index: 343

Text #6

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.4016. Min Act: -0.0000

Data Index: 96594 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.2521. Min Act: -0.0000

Data Index: 527895 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.3232. Min Act: -0.0000

Data Index: 269843 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.3978. Min Act: -0.0000

Data Index: 1278387 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.2991. Min Act: -0.0000

Data Index: 424841 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.3748. Min Act: -0.0000

Data Index: 933103 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.2870. Min Act: -0.0000

Data Index: 983591 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.2624. Min Act: -0.0000

Data Index: 907881 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.1993. Min Act: -0.0000

Data Index: 1017367 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.2158. Min Act: -0.0000

Data Index: 110204 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.2846. Min Act: -0.0000

Data Index: 518321 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.1845. Min Act: -0.0000

Data Index: 1304847 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.1803. Min Act: -0.0000

Data Index: 1019300 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.2540. Min Act: -0.0000

Data Index: 924913 (C4 (Web Text))

Max Activating Token Index: 88