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

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

Neuron 2887 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5806. Min Range: -2.5806

Max Act: 2.4742. Min Act: -0.0000

Data Index: 1652659 (Python Code)

Max Activating Token Index: 463

Text #1

Max Range: 2.5806. Min Range: -2.5806

Max Act: 2.5806. Min Act: -0.0000

Data Index: 255195 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 2.5806. Min Range: -2.5806

Max Act: 2.4981. Min Act: -0.0000

Data Index: 1117446 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 2.5806. Min Range: -2.5806

Max Act: 2.2966. Min Act: -0.0001

Data Index: 1587319 (Python Code)

Max Activating Token Index: 228

Text #4

Max Range: 2.5806. Min Range: -2.5806

Max Act: 2.3768. Min Act: -0.0000

Data Index: 72222 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 2.5806. Min Range: -2.5806

Max Act: 2.2388. Min Act: -0.0000

Data Index: 1489720 (Python Code)

Max Activating Token Index: 51

Text #6

Max Range: 2.5806. Min Range: -2.5806

Max Act: 2.0704. Min Act: -0.0000

Data Index: 1434682 (Python Code)

Max Activating Token Index: 758

Text #7

Max Range: 2.5806. Min Range: -2.5806

Max Act: 2.0374. Min Act: -0.0000

Data Index: 796406 (C4 (Web Text))

Max Activating Token Index: 676

Text #8

Max Range: 2.5806. Min Range: -2.5806

Max Act: 2.0354. Min Act: -0.0001

Data Index: 1379018 (Python Code)

Max Activating Token Index: 163

Text #9

Max Range: 2.5806. Min Range: -2.5806

Max Act: 2.1509. Min Act: -0.0000

Data Index: 163701 (C4 (Web Text))

Max Activating Token Index: 965

Text #10

Max Range: 2.5806. Min Range: -2.5806

Max Act: 2.0243. Min Act: -0.0001

Data Index: 1506029 (Python Code)

Max Activating Token Index: 28

Text #11

Max Range: 2.5806. Min Range: -2.5806

Max Act: 1.9824. Min Act: -0.0001

Data Index: 1619127 (Python Code)

Max Activating Token Index: 345

Text #12

Max Range: 2.5806. Min Range: -2.5806

Max Act: 1.9728. Min Act: -0.0000

Data Index: 1551890 (Python Code)

Max Activating Token Index: 58

Text #13

Max Range: 2.5806. Min Range: -2.5806

Max Act: 2.0783. Min Act: -0.0000

Data Index: 1559999 (Python Code)

Max Activating Token Index: 314

Text #14

Max Range: 2.5806. Min Range: -2.5806

Max Act: 1.9719. Min Act: -0.0000

Data Index: 34592 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 2.5806. Min Range: -2.5806

Max Act: 1.8620. Min Act: -0.0000

Data Index: 1577893 (Python Code)

Max Activating Token Index: 766

Text #16

Max Range: 2.5806. Min Range: -2.5806

Max Act: 2.0601. Min Act: -0.0001

Data Index: 818712 (C4 (Web Text))

Max Activating Token Index: 646

Text #17

Max Range: 2.5806. Min Range: -2.5806

Max Act: 2.0312. Min Act: -0.0000

Data Index: 1634169 (Python Code)

Max Activating Token Index: 298

Text #18

Max Range: 2.5806. Min Range: -2.5806

Max Act: 1.9199. Min Act: -0.0000

Data Index: 1361233 (Python Code)

Max Activating Token Index: 298

Text #19

Max Range: 2.5806. Min Range: -2.5806

Max Act: 2.0205. Min Act: -0.0000

Data Index: 1462841 (Python Code)

Max Activating Token Index: 387