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

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

Neuron 4859 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1179. Min Range: -1.1179

Max Act: 1.1179. Min Act: -0.0000

Data Index: 304063 (C4 (Web Text))

Max Activating Token Index: 779

Text #1

Max Range: 1.1179. Min Range: -1.1179

Max Act: 1.0674. Min Act: 0.0000

Data Index: 1170951 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 1.1179. Min Range: -1.1179

Max Act: 1.0602. Min Act: -0.0000

Data Index: 625294 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 1.1179. Min Range: -1.1179

Max Act: 1.0692. Min Act: -0.0000

Data Index: 195031 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.9430. Min Act: -0.0000

Data Index: 876982 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.9544. Min Act: 0.0002

Data Index: 36501 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.9486. Min Act: -0.0000

Data Index: 1141277 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.9618. Min Act: -0.0000

Data Index: 140370 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.9421. Min Act: -0.0000

Data Index: 1125215 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.9087. Min Act: -0.0000

Data Index: 1314133 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.9235. Min Act: -0.0000

Data Index: 543554 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.9458. Min Act: -0.0000

Data Index: 954265 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.9120. Min Act: -0.0000

Data Index: 27176 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.9400. Min Act: -0.0000

Data Index: 211084 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8783. Min Act: 0.0000

Data Index: 818067 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8567. Min Act: -0.0000

Data Index: 1056176 (C4 (Web Text))

Max Activating Token Index: 796

Text #16

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8672. Min Act: -0.0000

Data Index: 150080 (C4 (Web Text))

Max Activating Token Index: 234

Text #17

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8762. Min Act: -0.0000

Data Index: 1343715 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8314. Min Act: 0.0001

Data Index: 1256104 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8263. Min Act: -0.0000

Data Index: 1012387 (C4 (Web Text))

Max Activating Token Index: 246