Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3054 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.1055. Min Act: -0.0000

Data Index: 1057750 (C4 (Web Text))

Max Activating Token Index: 368

Text #1

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.1017. Min Act: -0.0000

Data Index: 1005422 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0985. Min Act: -0.0001

Data Index: 697362 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0908. Min Act: -0.0000

Data Index: 803550 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0881. Min Act: -0.0000

Data Index: 417661 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0848. Min Act: -0.0000

Data Index: 180102 (C4 (Web Text))

Max Activating Token Index: 847

Text #6

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0937. Min Act: -0.0000

Data Index: 1324109 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0821. Min Act: -0.0000

Data Index: 1024958 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0765. Min Act: -0.0001

Data Index: 40330 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0846. Min Act: -0.0000

Data Index: 433802 (C4 (Web Text))

Max Activating Token Index: 781

Text #10

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0813. Min Act: -0.0001

Data Index: 875412 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0799. Min Act: -0.0000

Data Index: 1211178 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0783. Min Act: -0.0001

Data Index: 1086074 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0778. Min Act: -0.0000

Data Index: 389173 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0799. Min Act: -0.0000

Data Index: 611891 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0797. Min Act: -0.0001

Data Index: 1309605 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0765. Min Act: -0.0001

Data Index: 411362 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0851. Min Act: -0.0001

Data Index: 837117 (C4 (Web Text))

Max Activating Token Index: 678

Text #18

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0848. Min Act: -0.0000

Data Index: 993768 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0732. Min Act: -0.0000

Data Index: 758001 (C4 (Web Text))

Max Activating Token Index: 251