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

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

Neuron 5466 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: 5.5927. Min Range: -5.5927

Max Act: 5.5927. Min Act: -0.0000

Data Index: 570197 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 5.5927. Min Range: -5.5927

Max Act: 5.5704. Min Act: -0.0000

Data Index: 1347142 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 5.5927. Min Range: -5.5927

Max Act: 5.1970. Min Act: -0.0000

Data Index: 1299721 (C4 (Web Text))

Max Activating Token Index: 342

Text #3

Max Range: 5.5927. Min Range: -5.5927

Max Act: 5.2521. Min Act: -0.0000

Data Index: 82923 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 5.5927. Min Range: -5.5927

Max Act: 4.9292. Min Act: -0.0000

Data Index: 992237 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 5.5927. Min Range: -5.5927

Max Act: 5.2963. Min Act: -0.0000

Data Index: 518980 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 5.5927. Min Range: -5.5927

Max Act: 5.0425. Min Act: -0.0000

Data Index: 541642 (C4 (Web Text))

Max Activating Token Index: 461

Text #7

Max Range: 5.5927. Min Range: -5.5927

Max Act: 5.0719. Min Act: -0.0000

Data Index: 958462 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 5.5927. Min Range: -5.5927

Max Act: 5.0530. Min Act: -0.0000

Data Index: 149999 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 5.5927. Min Range: -5.5927

Max Act: 4.9710. Min Act: -0.0000

Data Index: 876898 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 5.5927. Min Range: -5.5927

Max Act: 4.9497. Min Act: -0.0000

Data Index: 341294 (C4 (Web Text))

Max Activating Token Index: 521

Text #11

Max Range: 5.5927. Min Range: -5.5927

Max Act: 4.6700. Min Act: -0.0000

Data Index: 1139117 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 5.5927. Min Range: -5.5927

Max Act: 4.6289. Min Act: -0.0000

Data Index: 211260 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 5.5927. Min Range: -5.5927

Max Act: 4.7773. Min Act: -0.0000

Data Index: 1066836 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 5.5927. Min Range: -5.5927

Max Act: 4.7830. Min Act: -0.0000

Data Index: 768502 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 5.5927. Min Range: -5.5927

Max Act: 4.5601. Min Act: -0.0000

Data Index: 739620 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 5.5927. Min Range: -5.5927

Max Act: 4.5484. Min Act: -0.0000

Data Index: 1165321 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 5.5927. Min Range: -5.5927

Max Act: 4.5236. Min Act: -0.0000

Data Index: 40504 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 5.5927. Min Range: -5.5927

Max Act: 4.5095. Min Act: -0.0000

Data Index: 180072 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 5.5927. Min Range: -5.5927

Max Act: 4.6846. Min Act: -0.0000

Data Index: 57314 (C4 (Web Text))

Max Activating Token Index: 444