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

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

Neuron 5553 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.8527. Min Act: -0.0000

Data Index: 1303122 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6918. Min Act: -0.0000

Data Index: 888072 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6509. Min Act: 0.0000

Data Index: 1344995 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6527. Min Act: -0.0000

Data Index: 1336920 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6433. Min Act: -0.0000

Data Index: 1030805 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6590. Min Act: -0.0000

Data Index: 499554 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6597. Min Act: -0.0000

Data Index: 617757 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6312. Min Act: 0.0000

Data Index: 586187 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6449. Min Act: -0.0000

Data Index: 1004879 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.5901. Min Act: -0.0000

Data Index: 51264 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6137. Min Act: -0.0000

Data Index: 600800 (C4 (Web Text))

Max Activating Token Index: 618

Text #11

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6140. Min Act: -0.0000

Data Index: 394875 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6085. Min Act: -0.0000

Data Index: 1086101 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.5739. Min Act: -0.0000

Data Index: 239097 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.5630. Min Act: -0.0000

Data Index: 1560511 (Python Code)

Max Activating Token Index: 86

Text #15

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.5632. Min Act: 0.0003

Data Index: 1088435 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6170. Min Act: -0.0000

Data Index: 90018 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.5770. Min Act: 0.0004

Data Index: 182641 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.5726. Min Act: -0.0000

Data Index: 1026759 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.5566. Min Act: -0.0000

Data Index: 1606217 (Python Code)

Max Activating Token Index: 360