Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1839 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.1093. Min Act: -0.0001

Data Index: 1228979 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.1014. Min Act: -0.0001

Data Index: 249066 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0952. Min Act: -0.0001

Data Index: 881489 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0982. Min Act: -0.0001

Data Index: 1089807 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0905. Min Act: -0.0001

Data Index: 224754 (C4 (Web Text))

Max Activating Token Index: 337

Text #5

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0978. Min Act: -0.0001

Data Index: 1026428 (C4 (Web Text))

Max Activating Token Index: 712

Text #6

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0982. Min Act: -0.0001

Data Index: 1252115 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0936. Min Act: -0.0001

Data Index: 1036479 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0881. Min Act: -0.0001

Data Index: 172701 (C4 (Web Text))

Max Activating Token Index: 528

Text #9

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0934. Min Act: -0.0001

Data Index: 940599 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0830. Min Act: -0.0001

Data Index: 150678 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0903. Min Act: -0.0001

Data Index: 700978 (C4 (Web Text))

Max Activating Token Index: 761

Text #12

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0816. Min Act: -0.0001

Data Index: 1253982 (C4 (Web Text))

Max Activating Token Index: 719

Text #13

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0865. Min Act: -0.0001

Data Index: 968150 (C4 (Web Text))

Max Activating Token Index: 348

Text #14

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0847. Min Act: -0.0001

Data Index: 826896 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0805. Min Act: -0.0001

Data Index: 594891 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0811. Min Act: -0.0001

Data Index: 1213232 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0831. Min Act: -0.0001

Data Index: 434065 (C4 (Web Text))

Max Activating Token Index: 486

Text #18

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0795. Min Act: -0.0001

Data Index: 1087600 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0771. Min Act: -0.0001

Data Index: 1078698 (C4 (Web Text))

Max Activating Token Index: 983