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

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

Neuron 778 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7511. Min Range: -5.7511

Max Act: 5.7511. Min Act: -0.0000

Data Index: 749102 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 5.7511. Min Range: -5.7511

Max Act: 5.5344. Min Act: -0.0000

Data Index: 201672 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 5.7511. Min Range: -5.7511

Max Act: 5.1805. Min Act: -0.0000

Data Index: 1341171 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 5.7511. Min Range: -5.7511

Max Act: 5.1712. Min Act: -0.0001

Data Index: 989850 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 5.7511. Min Range: -5.7511

Max Act: 4.6042. Min Act: -0.0000

Data Index: 817632 (C4 (Web Text))

Max Activating Token Index: 355

Text #5

Max Range: 5.7511. Min Range: -5.7511

Max Act: 4.4087. Min Act: -0.0001

Data Index: 1211116 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 5.7511. Min Range: -5.7511

Max Act: 4.4048. Min Act: -0.0001

Data Index: 77410 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 5.7511. Min Range: -5.7511

Max Act: 4.8283. Min Act: -0.0000

Data Index: 944707 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 5.7511. Min Range: -5.7511

Max Act: 4.7739. Min Act: -0.0000

Data Index: 516413 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 5.7511. Min Range: -5.7511

Max Act: 4.2911. Min Act: -0.0000

Data Index: 1117786 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 5.7511. Min Range: -5.7511

Max Act: 4.6027. Min Act: -0.0001

Data Index: 82172 (C4 (Web Text))

Max Activating Token Index: 397

Text #11

Max Range: 5.7511. Min Range: -5.7511

Max Act: 4.3881. Min Act: -0.0001

Data Index: 500325 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 5.7511. Min Range: -5.7511

Max Act: 4.1499. Min Act: -0.0000

Data Index: 1316911 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 5.7511. Min Range: -5.7511

Max Act: 3.9942. Min Act: -0.0001

Data Index: 1216382 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 5.7511. Min Range: -5.7511

Max Act: 4.2764. Min Act: -0.0000

Data Index: 1051451 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 5.7511. Min Range: -5.7511

Max Act: 4.2793. Min Act: -0.0001

Data Index: 110905 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 5.7511. Min Range: -5.7511

Max Act: 3.8728. Min Act: -0.0000

Data Index: 1120063 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 5.7511. Min Range: -5.7511

Max Act: 3.7229. Min Act: -0.0001

Data Index: 603777 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 5.7511. Min Range: -5.7511

Max Act: 4.5683. Min Act: -0.0001

Data Index: 123851 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 5.7511. Min Range: -5.7511

Max Act: 4.3824. Min Act: -0.0000

Data Index: 230294 (C4 (Web Text))

Max Activating Token Index: 269