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

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

Neuron 640 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4987. Min Range: -1.4987

Max Act: 1.4987. Min Act: -0.0001

Data Index: 915397 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 1.4987. Min Range: -1.4987

Max Act: 1.2046. Min Act: -0.0001

Data Index: 796113 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 1.4987. Min Range: -1.4987

Max Act: 1.1269. Min Act: -0.0002

Data Index: 582062 (C4 (Web Text))

Max Activating Token Index: 762

Text #3

Max Range: 1.4987. Min Range: -1.4987

Max Act: 1.0869. Min Act: -0.0002

Data Index: 162145 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 1.4987. Min Range: -1.4987

Max Act: 1.0747. Min Act: -0.0002

Data Index: 1201119 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 1.4987. Min Range: -1.4987

Max Act: 1.0923. Min Act: -0.0002

Data Index: 848010 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 1.4987. Min Range: -1.4987

Max Act: 1.0383. Min Act: -0.0002

Data Index: 1071095 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 1.4987. Min Range: -1.4987

Max Act: 1.0247. Min Act: -0.0002

Data Index: 478421 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 1.4987. Min Range: -1.4987

Max Act: 1.0295. Min Act: -0.0002

Data Index: 1277074 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 1.4987. Min Range: -1.4987

Max Act: 0.9984. Min Act: -0.0002

Data Index: 930216 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 1.4987. Min Range: -1.4987

Max Act: 0.9868. Min Act: -0.0002

Data Index: 217223 (C4 (Web Text))

Max Activating Token Index: 838

Text #11

Max Range: 1.4987. Min Range: -1.4987

Max Act: 0.9827. Min Act: -0.0002

Data Index: 662126 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 1.4987. Min Range: -1.4987

Max Act: 0.9732. Min Act: -0.0001

Data Index: 595476 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 1.4987. Min Range: -1.4987

Max Act: 0.9403. Min Act: -0.0001

Data Index: 474778 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 1.4987. Min Range: -1.4987

Max Act: 0.9999. Min Act: -0.0002

Data Index: 625278 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 1.4987. Min Range: -1.4987

Max Act: 0.9642. Min Act: -0.0002

Data Index: 99101 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 1.4987. Min Range: -1.4987

Max Act: 0.9570. Min Act: -0.0002

Data Index: 53409 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 1.4987. Min Range: -1.4987

Max Act: 0.9513. Min Act: -0.0002

Data Index: 534797 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 1.4987. Min Range: -1.4987

Max Act: 1.0378. Min Act: -0.0002

Data Index: 600160 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 1.4987. Min Range: -1.4987

Max Act: 0.9522. Min Act: -0.0002

Data Index: 7496 (C4 (Web Text))

Max Activating Token Index: 87