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

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

Neuron 5981 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: 1.7715. Min Range: -1.7715

Max Act: 1.7715. Min Act: -0.0000

Data Index: 561868 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 1.7715. Min Range: -1.7715

Max Act: 1.4483. Min Act: -0.0000

Data Index: 83750 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 1.7715. Min Range: -1.7715

Max Act: 1.6841. Min Act: -0.0000

Data Index: 1102753 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 1.7715. Min Range: -1.7715

Max Act: 1.5978. Min Act: -0.0000

Data Index: 96142 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 1.7715. Min Range: -1.7715

Max Act: 1.5290. Min Act: -0.0000

Data Index: 1137136 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 1.7715. Min Range: -1.7715

Max Act: 1.4806. Min Act: -0.0000

Data Index: 254170 (C4 (Web Text))

Max Activating Token Index: 410

Text #6

Max Range: 1.7715. Min Range: -1.7715

Max Act: 1.4262. Min Act: -0.0001

Data Index: 977234 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 1.7715. Min Range: -1.7715

Max Act: 1.3473. Min Act: -0.0000

Data Index: 951175 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 1.7715. Min Range: -1.7715

Max Act: 1.4973. Min Act: -0.0001

Data Index: 145284 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 1.7715. Min Range: -1.7715

Max Act: 1.5156. Min Act: -0.0000

Data Index: 513081 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 1.7715. Min Range: -1.7715

Max Act: 1.4712. Min Act: -0.0000

Data Index: 1265386 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 1.7715. Min Range: -1.7715

Max Act: 1.3892. Min Act: -0.0000

Data Index: 649039 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 1.7715. Min Range: -1.7715

Max Act: 1.4117. Min Act: -0.0000

Data Index: 633307 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 1.7715. Min Range: -1.7715

Max Act: 1.4551. Min Act: -0.0000

Data Index: 1202074 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 1.7715. Min Range: -1.7715

Max Act: 1.3877. Min Act: -0.0000

Data Index: 968016 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 1.7715. Min Range: -1.7715

Max Act: 1.5964. Min Act: -0.0000

Data Index: 163126 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 1.7715. Min Range: -1.7715

Max Act: 1.3687. Min Act: -0.0000

Data Index: 1306920 (C4 (Web Text))

Max Activating Token Index: 477

Text #17

Max Range: 1.7715. Min Range: -1.7715

Max Act: 1.3311. Min Act: -0.0000

Data Index: 16671 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 1.7715. Min Range: -1.7715

Max Act: 1.6095. Min Act: -0.0000

Data Index: 1099998 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 1.7715. Min Range: -1.7715

Max Act: 1.3760. Min Act: -0.0000

Data Index: 727567 (C4 (Web Text))

Max Activating Token Index: 28