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

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

Neuron 4792 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: 0.0983. Min Range: -0.0983

Max Act: 0.0983. Min Act: -0.0001

Data Index: 399229 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0939. Min Act: -0.0001

Data Index: 942484 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0868. Min Act: -0.0001

Data Index: 586443 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0836. Min Act: -0.0001

Data Index: 1528679 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0863. Min Act: -0.0001

Data Index: 286921 (C4 (Web Text))

Max Activating Token Index: 169

Text #5

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0812. Min Act: -0.0001

Data Index: 992108 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0837. Min Act: -0.0001

Data Index: 48005 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0797. Min Act: -0.0001

Data Index: 1306005 (C4 (Web Text))

Max Activating Token Index: 313

Text #8

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0721. Min Act: -0.0001

Data Index: 461608 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0792. Min Act: -0.0001

Data Index: 374303 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0747. Min Act: -0.0001

Data Index: 913575 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0691. Min Act: -0.0001

Data Index: 760555 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0674. Min Act: -0.0001

Data Index: 1148856 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0723. Min Act: -0.0001

Data Index: 1290462 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0477. Min Act: -0.0001

Data Index: 363143 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0653. Min Act: -0.0001

Data Index: 522902 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0766. Min Act: -0.0001

Data Index: 983691 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0780. Min Act: -0.0001

Data Index: 252258 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0681. Min Act: -0.0001

Data Index: 610387 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0604. Min Act: -0.0001

Data Index: 1346115 (C4 (Web Text))

Max Activating Token Index: 365