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

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

Neuron 4202 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.3416. Min Range: -8.3416

Max Act: 8.3416. Min Act: -0.0000

Data Index: 446773 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 8.3416. Min Range: -8.3416

Max Act: 7.9462. Min Act: -0.0000

Data Index: 988925 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 8.3416. Min Range: -8.3416

Max Act: 7.2210. Min Act: -0.0000

Data Index: 157919 (C4 (Web Text))

Max Activating Token Index: 985

Text #3

Max Range: 8.3416. Min Range: -8.3416

Max Act: 6.8837. Min Act: -0.0000

Data Index: 872968 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 8.3416. Min Range: -8.3416

Max Act: 6.7177. Min Act: -0.0000

Data Index: 352122 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 8.3416. Min Range: -8.3416

Max Act: 6.5509. Min Act: -0.0000

Data Index: 502686 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 8.3416. Min Range: -8.3416

Max Act: 6.4556. Min Act: -0.0000

Data Index: 1015827 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 8.3416. Min Range: -8.3416

Max Act: 6.4342. Min Act: -0.0000

Data Index: 385864 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 8.3416. Min Range: -8.3416

Max Act: 6.0098. Min Act: -0.0000

Data Index: 1067422 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 8.3416. Min Range: -8.3416

Max Act: 5.9726. Min Act: -0.0000

Data Index: 994481 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 8.3416. Min Range: -8.3416

Max Act: 6.2445. Min Act: -0.0000

Data Index: 1257809 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 8.3416. Min Range: -8.3416

Max Act: 5.8216. Min Act: -0.0000

Data Index: 933647 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 8.3416. Min Range: -8.3416

Max Act: 5.8007. Min Act: -0.0000

Data Index: 333343 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 8.3416. Min Range: -8.3416

Max Act: 5.7736. Min Act: -0.0000

Data Index: 788683 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 8.3416. Min Range: -8.3416

Max Act: 6.1533. Min Act: -0.0000

Data Index: 568031 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 8.3416. Min Range: -8.3416

Max Act: 5.8960. Min Act: -0.0000

Data Index: 1053053 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 8.3416. Min Range: -8.3416

Max Act: 6.0592. Min Act: -0.0000

Data Index: 457387 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 8.3416. Min Range: -8.3416

Max Act: 6.4488. Min Act: -0.0000

Data Index: 690561 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 8.3416. Min Range: -8.3416

Max Act: 5.6308. Min Act: -0.0000

Data Index: 123106 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 8.3416. Min Range: -8.3416

Max Act: 5.7972. Min Act: -0.0000

Data Index: 1076141 (C4 (Web Text))

Max Activating Token Index: 570