Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2113 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1167. Min Act: -0.0001

Data Index: 687430 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1132. Min Act: -0.0001

Data Index: 502591 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1076. Min Act: -0.0001

Data Index: 183161 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1038. Min Act: -0.0001

Data Index: 388060 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1040. Min Act: -0.0001

Data Index: 848730 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1031. Min Act: -0.0001

Data Index: 1224536 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1000. Min Act: -0.0001

Data Index: 238362 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1015. Min Act: -0.0001

Data Index: 746273 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1006. Min Act: -0.0001

Data Index: 632112 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1005. Min Act: -0.0001

Data Index: 490443 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1008. Min Act: -0.0001

Data Index: 247859 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0913. Min Act: -0.0001

Data Index: 1164183 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0979. Min Act: -0.0001

Data Index: 159191 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0970. Min Act: -0.0001

Data Index: 273355 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0882. Min Act: -0.0001

Data Index: 692997 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0902. Min Act: -0.0001

Data Index: 493616 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0920. Min Act: -0.0001

Data Index: 980379 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0976. Min Act: -0.0001

Data Index: 1268966 (C4 (Web Text))

Max Activating Token Index: 572

Text #18

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0909. Min Act: -0.0001

Data Index: 396964 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0936. Min Act: -0.0001

Data Index: 142657 (C4 (Web Text))

Max Activating Token Index: 640