Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 780 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.5563. Min Act: -0.0001

Data Index: 657000 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.4855. Min Act: -0.0000

Data Index: 1342302 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.4036. Min Act: -0.0000

Data Index: 955047 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.4024. Min Act: -0.0000

Data Index: 931828 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.3881. Min Act: -0.0000

Data Index: 536893 (C4 (Web Text))

Max Activating Token Index: 389

Text #5

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.3754. Min Act: -0.0000

Data Index: 1307819 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.3869. Min Act: -0.0000

Data Index: 1000251 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.3702. Min Act: -0.0001

Data Index: 371021 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.3643. Min Act: -0.0000

Data Index: 825787 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.3633. Min Act: -0.0001

Data Index: 955813 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.3640. Min Act: -0.0001

Data Index: 1196002 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.3762. Min Act: -0.0000

Data Index: 1308225 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.3843. Min Act: -0.0000

Data Index: 1257768 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.3691. Min Act: -0.0001

Data Index: 1002149 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.3580. Min Act: -0.0000

Data Index: 1022602 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.3559. Min Act: -0.0000

Data Index: 1089819 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.3591. Min Act: -0.0000

Data Index: 28472 (C4 (Web Text))

Max Activating Token Index: 486

Text #17

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.3361. Min Act: -0.0001

Data Index: 42199 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.3458. Min Act: -0.0000

Data Index: 1240821 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.3336. Min Act: -0.0000

Data Index: 305239 (C4 (Web Text))

Max Activating Token Index: 312