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

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

Neuron 5543 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.1121. Min Act: -0.0000

Data Index: 34036 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0964. Min Act: -0.0000

Data Index: 235887 (C4 (Web Text))

Max Activating Token Index: 264

Text #2

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.1027. Min Act: -0.0000

Data Index: 1022020 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.1056. Min Act: -0.0000

Data Index: 145999 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0712. Min Act: -0.0000

Data Index: 1335180 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0989. Min Act: -0.0000

Data Index: 728241 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0997. Min Act: -0.0000

Data Index: 27267 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.1025. Min Act: -0.0000

Data Index: 187395 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.1018. Min Act: -0.0000

Data Index: 759616 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0961. Min Act: -0.0000

Data Index: 417557 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0997. Min Act: -0.0000

Data Index: 1103930 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0985. Min Act: -0.0000

Data Index: 1185939 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0998. Min Act: -0.0000

Data Index: 1177786 (C4 (Web Text))

Max Activating Token Index: 416

Text #13

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0873. Min Act: -0.0000

Data Index: 437897 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0954. Min Act: -0.0000

Data Index: 143806 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0989. Min Act: -0.0000

Data Index: 1521418 (Python Code)

Max Activating Token Index: 246

Text #16

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0977. Min Act: -0.0000

Data Index: 1101748 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0852. Min Act: -0.0000

Data Index: 1479922 (Python Code)

Max Activating Token Index: 247

Text #18

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0971. Min Act: -0.0000

Data Index: 300868 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0927. Min Act: -0.0000

Data Index: 1147726 (C4 (Web Text))

Max Activating Token Index: 642