Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2396 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.8748. Min Act: -0.0000

Data Index: 213208 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.4991. Min Act: -0.0000

Data Index: 735253 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.5274. Min Act: -0.0000

Data Index: 336478 (C4 (Web Text))

Max Activating Token Index: 567

Text #3

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.6084. Min Act: -0.0000

Data Index: 1299498 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.5507. Min Act: -0.0000

Data Index: 1225403 (C4 (Web Text))

Max Activating Token Index: 469

Text #5

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.4619. Min Act: -0.0000

Data Index: 550796 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.4412. Min Act: -0.0000

Data Index: 139286 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.4354. Min Act: -0.0000

Data Index: 1262197 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.4154. Min Act: -0.0000

Data Index: 635420 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.3363. Min Act: -0.0000

Data Index: 826229 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.3981. Min Act: -0.0000

Data Index: 702727 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.5489. Min Act: -0.0000

Data Index: 101236 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.2992. Min Act: -0.0000

Data Index: 812385 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.3766. Min Act: -0.0000

Data Index: 1058803 (C4 (Web Text))

Max Activating Token Index: 576

Text #14

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.3558. Min Act: -0.0000

Data Index: 303244 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.3274. Min Act: -0.0000

Data Index: 812313 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.3865. Min Act: -0.0000

Data Index: 458554 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.2959. Min Act: -0.0000

Data Index: 29692 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.2446. Min Act: -0.0000

Data Index: 879906 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.3199. Min Act: -0.0000

Data Index: 923675 (C4 (Web Text))

Max Activating Token Index: 943