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

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

Neuron 1787 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: 0.1378. Min Range: -0.1378

Max Act: 0.1378. Min Act: -0.0001

Data Index: 1243800 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 0.1378. Min Range: -0.1378

Max Act: 0.1228. Min Act: -0.0001

Data Index: 285511 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 0.1378. Min Range: -0.1378

Max Act: 0.1211. Min Act: -0.0001

Data Index: 139142 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 0.1378. Min Range: -0.1378

Max Act: 0.1152. Min Act: -0.0001

Data Index: 534672 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 0.1378. Min Range: -0.1378

Max Act: 0.1112. Min Act: -0.0001

Data Index: 277681 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 0.1378. Min Range: -0.1378

Max Act: 0.0987. Min Act: -0.0001

Data Index: 1232080 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 0.1378. Min Range: -0.1378

Max Act: 0.1049. Min Act: -0.0001

Data Index: 516576 (C4 (Web Text))

Max Activating Token Index: 528

Text #7

Max Range: 0.1378. Min Range: -0.1378

Max Act: 0.1123. Min Act: -0.0001

Data Index: 951563 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.1378. Min Range: -0.1378

Max Act: 0.1074. Min Act: -0.0001

Data Index: 666397 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 0.1378. Min Range: -0.1378

Max Act: 0.1069. Min Act: -0.0001

Data Index: 4211 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 0.1378. Min Range: -0.1378

Max Act: 0.1095. Min Act: -0.0001

Data Index: 923030 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 0.1378. Min Range: -0.1378

Max Act: 0.1050. Min Act: -0.0001

Data Index: 129347 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 0.1378. Min Range: -0.1378

Max Act: 0.1063. Min Act: -0.0001

Data Index: 357561 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 0.1378. Min Range: -0.1378

Max Act: 0.1066. Min Act: -0.0001

Data Index: 118276 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 0.1378. Min Range: -0.1378

Max Act: 0.1015. Min Act: -0.0001

Data Index: 542950 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 0.1378. Min Range: -0.1378

Max Act: 0.1007. Min Act: -0.0001

Data Index: 1143666 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 0.1378. Min Range: -0.1378

Max Act: 0.1037. Min Act: -0.0001

Data Index: 821361 (C4 (Web Text))

Max Activating Token Index: 188

Text #17

Max Range: 0.1378. Min Range: -0.1378

Max Act: 0.0960. Min Act: -0.0001

Data Index: 1270797 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 0.1378. Min Range: -0.1378

Max Act: 0.0962. Min Act: -0.0001

Data Index: 1298738 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 0.1378. Min Range: -0.1378

Max Act: 0.0917. Min Act: -0.0001

Data Index: 768605 (C4 (Web Text))

Max Activating Token Index: 517