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

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

Neuron 4317 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: 0.1093. Min Range: -0.1093

Max Act: 0.1093. Min Act: -0.0001

Data Index: 724401 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0886. Min Act: -0.0001

Data Index: 976247 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.1004. Min Act: -0.0001

Data Index: 734220 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0924. Min Act: -0.0001

Data Index: 238026 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0939. Min Act: -0.0001

Data Index: 1269908 (C4 (Web Text))

Max Activating Token Index: 892

Text #5

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0897. Min Act: -0.0001

Data Index: 1337939 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0927. Min Act: -0.0001

Data Index: 287750 (C4 (Web Text))

Max Activating Token Index: 819

Text #7

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0831. Min Act: -0.0001

Data Index: 954549 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0816. Min Act: -0.0001

Data Index: 408617 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0718. Min Act: -0.0001

Data Index: 633556 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0840. Min Act: -0.0001

Data Index: 396810 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0794. Min Act: -0.0001

Data Index: 808583 (C4 (Web Text))

Max Activating Token Index: 961

Text #12

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0818. Min Act: -0.0001

Data Index: 465590 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0736. Min Act: -0.0001

Data Index: 617556 (C4 (Web Text))

Max Activating Token Index: 581

Text #14

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0771. Min Act: -0.0001

Data Index: 945560 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0777. Min Act: -0.0001

Data Index: 306574 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0777. Min Act: -0.0001

Data Index: 1272782 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0775. Min Act: -0.0001

Data Index: 72741 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0781. Min Act: -0.0001

Data Index: 601590 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0812. Min Act: -0.0001

Data Index: 656702 (C4 (Web Text))

Max Activating Token Index: 314