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

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

Neuron 6087 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: 1.3867. Min Range: -1.3867

Max Act: 1.3867. Min Act: -0.0000

Data Index: 977886 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.3013. Min Act: -0.0000

Data Index: 196212 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.2996. Min Act: -0.0000

Data Index: 1230437 (C4 (Web Text))

Max Activating Token Index: 838

Text #3

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.1640. Min Act: -0.0000

Data Index: 11223 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.1251. Min Act: -0.0000

Data Index: 141949 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.0610. Min Act: -0.0000

Data Index: 632443 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.0908. Min Act: -0.0000

Data Index: 1069698 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 1.3867. Min Range: -1.3867

Max Act: 0.9566. Min Act: -0.0000

Data Index: 831878 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 1.3867. Min Range: -1.3867

Max Act: 0.9447. Min Act: -0.0000

Data Index: 1063198 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 1.3867. Min Range: -1.3867

Max Act: 0.9213. Min Act: -0.0000

Data Index: 772348 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 1.3867. Min Range: -1.3867

Max Act: 0.9542. Min Act: -0.0000

Data Index: 970598 (C4 (Web Text))

Max Activating Token Index: 983

Text #11

Max Range: 1.3867. Min Range: -1.3867

Max Act: 0.8353. Min Act: -0.0000

Data Index: 1330724 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 1.3867. Min Range: -1.3867

Max Act: 0.8218. Min Act: -0.0000

Data Index: 617602 (C4 (Web Text))

Max Activating Token Index: 921

Text #13

Max Range: 1.3867. Min Range: -1.3867

Max Act: 0.8621. Min Act: -0.0000

Data Index: 1347752 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 1.3867. Min Range: -1.3867

Max Act: 0.8389. Min Act: -0.0000

Data Index: 139261 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 1.3867. Min Range: -1.3867

Max Act: 0.7969. Min Act: -0.0000

Data Index: 1059948 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 1.3867. Min Range: -1.3867

Max Act: 0.7316. Min Act: -0.0000

Data Index: 11687 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 1.3867. Min Range: -1.3867

Max Act: 0.7786. Min Act: -0.0000

Data Index: 526990 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 1.3867. Min Range: -1.3867

Max Act: 0.7967. Min Act: -0.0000

Data Index: 1298993 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 1.3867. Min Range: -1.3867

Max Act: 0.7806. Min Act: -0.0000

Data Index: 1133082 (C4 (Web Text))

Max Activating Token Index: 984