Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2323 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.5693. Min Act: -0.0001

Data Index: 319913 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.5230. Min Act: -0.0001

Data Index: 1618348 (Python Code)

Max Activating Token Index: 146

Text #2

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.5624. Min Act: -0.0001

Data Index: 1353892 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.4882. Min Act: -0.0001

Data Index: 749035 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.5022. Min Act: -0.0001

Data Index: 1105692 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.5067. Min Act: -0.0001

Data Index: 531551 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.4965. Min Act: -0.0001

Data Index: 1348496 (C4 (Web Text))

Max Activating Token Index: 953

Text #7

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.5547. Min Act: -0.0001

Data Index: 1611007 (Python Code)

Max Activating Token Index: 802

Text #8

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.5047. Min Act: -0.0001

Data Index: 583505 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.5010. Min Act: -0.0001

Data Index: 499221 (C4 (Web Text))

Max Activating Token Index: 922

Text #10

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.5001. Min Act: -0.0001

Data Index: 1411589 (Python Code)

Max Activating Token Index: 24

Text #11

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.4810. Min Act: -0.0001

Data Index: 1179732 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.4816. Min Act: -0.0001

Data Index: 1550684 (Python Code)

Max Activating Token Index: 739

Text #13

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.4715. Min Act: -0.0001

Data Index: 1389199 (Python Code)

Max Activating Token Index: 177

Text #14

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.4944. Min Act: -0.0001

Data Index: 1487757 (Python Code)

Max Activating Token Index: 51

Text #15

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.4649. Min Act: -0.0001

Data Index: 1181245 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.4366. Min Act: -0.0001

Data Index: 1282627 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.4587. Min Act: -0.0001

Data Index: 448797 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.4714. Min Act: -0.0001

Data Index: 817830 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.4815. Min Act: -0.0001

Data Index: 516249 (C4 (Web Text))

Max Activating Token Index: 325