Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 933 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.7456. Min Act: -0.0001

Data Index: 745003 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.7194. Min Act: -0.0001

Data Index: 1250920 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.7599. Min Act: -0.0000

Data Index: 844187 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.7367. Min Act: -0.0001

Data Index: 1377664 (Python Code)

Max Activating Token Index: 211

Text #4

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.7050. Min Act: -0.0000

Data Index: 400746 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.6744. Min Act: -0.0000

Data Index: 1244865 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.6977. Min Act: -0.0001

Data Index: 871656 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.6644. Min Act: -0.0000

Data Index: 162861 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.6171. Min Act: -0.0000

Data Index: 1041121 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.6392. Min Act: -0.0001

Data Index: 582293 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.6298. Min Act: -0.0001

Data Index: 1300837 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.6057. Min Act: -0.0000

Data Index: 940324 (C4 (Web Text))

Max Activating Token Index: 225

Text #12

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.5966. Min Act: -0.0001

Data Index: 1590844 (Python Code)

Max Activating Token Index: 399

Text #13

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.6094. Min Act: -0.0000

Data Index: 802225 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.5726. Min Act: -0.0001

Data Index: 140755 (C4 (Web Text))

Max Activating Token Index: 491

Text #15

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.5737. Min Act: -0.0001

Data Index: 1563786 (Python Code)

Max Activating Token Index: 531

Text #16

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.5768. Min Act: -0.0001

Data Index: 374037 (C4 (Web Text))

Max Activating Token Index: 322

Text #17

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.5496. Min Act: -0.0000

Data Index: 906466 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.5444. Min Act: -0.0000

Data Index: 867056 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.5614. Min Act: -0.0001

Data Index: 1598696 (Python Code)

Max Activating Token Index: 396