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

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

Neuron 2866 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.5714. Min Act: -0.0003

Data Index: 62105 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.5537. Min Act: -0.0003

Data Index: 1158757 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.4117. Min Act: -0.0003

Data Index: 869629 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.4887. Min Act: -0.0003

Data Index: 779978 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.3812. Min Act: -0.0003

Data Index: 149286 (C4 (Web Text))

Max Activating Token Index: 657

Text #5

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.4247. Min Act: -0.0003

Data Index: 395729 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.4225. Min Act: -0.0003

Data Index: 104640 (C4 (Web Text))

Max Activating Token Index: 430

Text #7

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.3638. Min Act: -0.0003

Data Index: 530057 (C4 (Web Text))

Max Activating Token Index: 510

Text #8

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.4077. Min Act: -0.0003

Data Index: 904335 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.2993. Min Act: -0.0003

Data Index: 851733 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.2868. Min Act: -0.0003

Data Index: 612776 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.2892. Min Act: -0.0003

Data Index: 205451 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.1094. Min Act: -0.0003

Data Index: 225067 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.1495. Min Act: -0.0003

Data Index: 648154 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.0316. Min Act: -0.0003

Data Index: 841458 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.1593. Min Act: -0.0003

Data Index: 1031482 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.0468. Min Act: -0.0003

Data Index: 67456 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 1.5714. Min Range: -1.5714

Max Act: 0.9791. Min Act: -0.0003

Data Index: 1129733 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.0313. Min Act: -0.0003

Data Index: 1228727 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.0849. Min Act: -0.0003

Data Index: 48737 (C4 (Web Text))

Max Activating Token Index: 575