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

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

Neuron 2474 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.1139. Min Act: -0.0002

Data Index: 448486 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.1098. Min Act: -0.0002

Data Index: 1222973 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.1064. Min Act: -0.0002

Data Index: 1060308 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.1061. Min Act: -0.0002

Data Index: 838950 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.1040. Min Act: -0.0002

Data Index: 63534 (C4 (Web Text))

Max Activating Token Index: 467

Text #5

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.1035. Min Act: -0.0002

Data Index: 201570 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.1007. Min Act: -0.0002

Data Index: 692227 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.1054. Min Act: -0.0002

Data Index: 12860 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.1015. Min Act: -0.0002

Data Index: 1338925 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.1014. Min Act: -0.0002

Data Index: 392050 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.1005. Min Act: -0.0002

Data Index: 1224832 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.1018. Min Act: -0.0002

Data Index: 1159016 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.1009. Min Act: -0.0002

Data Index: 426763 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.1019. Min Act: -0.0002

Data Index: 470246 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.1019. Min Act: -0.0002

Data Index: 795098 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.1004. Min Act: -0.0002

Data Index: 247050 (C4 (Web Text))

Max Activating Token Index: 365

Text #16

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.0992. Min Act: -0.0002

Data Index: 246505 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.0984. Min Act: -0.0002

Data Index: 419275 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.1001. Min Act: -0.0002

Data Index: 941768 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.0987. Min Act: -0.0002

Data Index: 761664 (C4 (Web Text))

Max Activating Token Index: 422