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

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

Neuron 4580 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.2270. Min Act: -0.0001

Data Index: 960702 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.2123. Min Act: -0.0001

Data Index: 904335 (C4 (Web Text))

Max Activating Token Index: 424

Text #2

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.2135. Min Act: -0.0001

Data Index: 1050950 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.2107. Min Act: -0.0001

Data Index: 614378 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.2027. Min Act: -0.0001

Data Index: 637228 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.2122. Min Act: -0.0001

Data Index: 54785 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1976. Min Act: -0.0001

Data Index: 356060 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1926. Min Act: -0.0001

Data Index: 217191 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1865. Min Act: -0.0001

Data Index: 667210 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1726. Min Act: -0.0001

Data Index: 766454 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1718. Min Act: -0.0001

Data Index: 813252 (C4 (Web Text))

Max Activating Token Index: 440

Text #11

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1867. Min Act: -0.0001

Data Index: 1137320 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1758. Min Act: -0.0001

Data Index: 1086555 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1736. Min Act: -0.0001

Data Index: 55831 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1852. Min Act: -0.0001

Data Index: 573488 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1861. Min Act: -0.0001

Data Index: 1078117 (C4 (Web Text))

Max Activating Token Index: 423

Text #16

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1759. Min Act: -0.0001

Data Index: 1285973 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1857. Min Act: -0.0001

Data Index: 1337215 (C4 (Web Text))

Max Activating Token Index: 509

Text #18

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1816. Min Act: -0.0001

Data Index: 518899 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1761. Min Act: -0.0001

Data Index: 178741 (C4 (Web Text))

Max Activating Token Index: 270