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

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

Neuron 798 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7006. Min Range: -5.7006

Max Act: 5.7006. Min Act: -0.0000

Data Index: 882342 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 5.7006. Min Range: -5.7006

Max Act: 5.1082. Min Act: -0.0000

Data Index: 700927 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 5.7006. Min Range: -5.7006

Max Act: 5.0165. Min Act: -0.0000

Data Index: 783401 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 5.7006. Min Range: -5.7006

Max Act: 4.9944. Min Act: -0.0000

Data Index: 856678 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 5.7006. Min Range: -5.7006

Max Act: 4.7519. Min Act: -0.0000

Data Index: 490192 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 5.7006. Min Range: -5.7006

Max Act: 4.7124. Min Act: -0.0000

Data Index: 420359 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 5.7006. Min Range: -5.7006

Max Act: 4.4212. Min Act: -0.0000

Data Index: 454579 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 5.7006. Min Range: -5.7006

Max Act: 4.4529. Min Act: -0.0000

Data Index: 1085545 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 5.7006. Min Range: -5.7006

Max Act: 4.5910. Min Act: -0.0000

Data Index: 1347987 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 5.7006. Min Range: -5.7006

Max Act: 4.5768. Min Act: -0.0000

Data Index: 785027 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 5.7006. Min Range: -5.7006

Max Act: 4.5200. Min Act: -0.0000

Data Index: 1237438 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 5.7006. Min Range: -5.7006

Max Act: 4.2949. Min Act: -0.0000

Data Index: 568832 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 5.7006. Min Range: -5.7006

Max Act: 4.6582. Min Act: -0.0000

Data Index: 649722 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 5.7006. Min Range: -5.7006

Max Act: 4.1869. Min Act: -0.0000

Data Index: 977673 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 5.7006. Min Range: -5.7006

Max Act: 4.5495. Min Act: -0.0000

Data Index: 725786 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 5.7006. Min Range: -5.7006

Max Act: 4.3083. Min Act: -0.0000

Data Index: 954402 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 5.7006. Min Range: -5.7006

Max Act: 3.7952. Min Act: -0.0000

Data Index: 89595 (C4 (Web Text))

Max Activating Token Index: 805

Text #17

Max Range: 5.7006. Min Range: -5.7006

Max Act: 4.2674. Min Act: -0.0000

Data Index: 515647 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 5.7006. Min Range: -5.7006

Max Act: 4.2461. Min Act: -0.0000

Data Index: 1173637 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 5.7006. Min Range: -5.7006

Max Act: 4.2628. Min Act: -0.0000

Data Index: 1147943 (C4 (Web Text))

Max Activating Token Index: 580