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

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

Neuron 453 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: 6.5922. Min Range: -6.5922

Max Act: 6.5922. Min Act: -0.0001

Data Index: 738248 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 6.5922. Min Range: -6.5922

Max Act: 6.5248. Min Act: -0.0001

Data Index: 1235429 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 6.5922. Min Range: -6.5922

Max Act: 6.4350. Min Act: -0.0001

Data Index: 677574 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 6.5922. Min Range: -6.5922

Max Act: 6.4187. Min Act: -0.0000

Data Index: 329534 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 6.5922. Min Range: -6.5922

Max Act: 6.5006. Min Act: -0.0001

Data Index: 1331066 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 6.5922. Min Range: -6.5922

Max Act: 5.8797. Min Act: -0.0000

Data Index: 955091 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 6.5922. Min Range: -6.5922

Max Act: 5.4773. Min Act: -0.0000

Data Index: 149482 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 6.5922. Min Range: -6.5922

Max Act: 5.9102. Min Act: -0.0000

Data Index: 513794 (C4 (Web Text))

Max Activating Token Index: 712

Text #8

Max Range: 6.5922. Min Range: -6.5922

Max Act: 5.8963. Min Act: -0.0001

Data Index: 1076326 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 6.5922. Min Range: -6.5922

Max Act: 5.5993. Min Act: -0.0000

Data Index: 1002931 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 6.5922. Min Range: -6.5922

Max Act: 5.7714. Min Act: -0.0000

Data Index: 557231 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 6.5922. Min Range: -6.5922

Max Act: 5.8528. Min Act: -0.0001

Data Index: 312314 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 6.5922. Min Range: -6.5922

Max Act: 5.8430. Min Act: -0.0000

Data Index: 625551 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 6.5922. Min Range: -6.5922

Max Act: 5.4715. Min Act: -0.0000

Data Index: 422524 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 6.5922. Min Range: -6.5922

Max Act: 5.5579. Min Act: -0.0000

Data Index: 680410 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 6.5922. Min Range: -6.5922

Max Act: 5.2006. Min Act: -0.0001

Data Index: 960839 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 6.5922. Min Range: -6.5922

Max Act: 5.5148. Min Act: -0.0000

Data Index: 94980 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 6.5922. Min Range: -6.5922

Max Act: 5.5432. Min Act: -0.0000

Data Index: 418638 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 6.5922. Min Range: -6.5922

Max Act: 5.6604. Min Act: -0.0000

Data Index: 1258917 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 6.5922. Min Range: -6.5922

Max Act: 5.5676. Min Act: -0.0000

Data Index: 1042326 (C4 (Web Text))

Max Activating Token Index: 392