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

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

Neuron 5615 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: 0.1043. Min Range: -0.1043

Max Act: 0.0989. Min Act: -0.0000

Data Index: 1444464 (Python Code)

Max Activating Token Index: 603

Text #1

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.1019. Min Act: -0.0000

Data Index: 715954 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0994. Min Act: -0.0000

Data Index: 526989 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.1043. Min Act: -0.0000

Data Index: 1620332 (Python Code)

Max Activating Token Index: 902

Text #4

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.1043. Min Act: -0.0000

Data Index: 214755 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0965. Min Act: -0.0000

Data Index: 1472914 (Python Code)

Max Activating Token Index: 850

Text #6

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.1018. Min Act: -0.0000

Data Index: 1501542 (Python Code)

Max Activating Token Index: 334

Text #7

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0895. Min Act: -0.0001

Data Index: 1545851 (Python Code)

Max Activating Token Index: 566

Text #8

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0870. Min Act: -0.0000

Data Index: 499140 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0913. Min Act: -0.0000

Data Index: 1023283 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0840. Min Act: -0.0000

Data Index: 1622027 (Python Code)

Max Activating Token Index: 944

Text #11

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0863. Min Act: -0.0000

Data Index: 1393480 (Python Code)

Max Activating Token Index: 572

Text #12

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0780. Min Act: -0.0000

Data Index: 880196 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0914. Min Act: -0.0001

Data Index: 562747 (C4 (Web Text))

Max Activating Token Index: 533

Text #14

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0911. Min Act: -0.0000

Data Index: 1570833 (Python Code)

Max Activating Token Index: 286

Text #15

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0838. Min Act: -0.0000

Data Index: 1380239 (Python Code)

Max Activating Token Index: 227

Text #16

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0863. Min Act: -0.0000

Data Index: 1537087 (Python Code)

Max Activating Token Index: 986

Text #17

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0862. Min Act: -0.0001

Data Index: 970617 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0743. Min Act: -0.0001

Data Index: 47941 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0794. Min Act: -0.0000

Data Index: 1283971 (C4 (Web Text))

Max Activating Token Index: 11