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

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

Neuron 3239 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1937. Min Range: -2.1937

Max Act: 2.1937. Min Act: -0.0000

Data Index: 1096758 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 2.1937. Min Range: -2.1937

Max Act: 1.9499. Min Act: -0.0000

Data Index: 172178 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 2.1937. Min Range: -2.1937

Max Act: 2.0111. Min Act: -0.0000

Data Index: 1570980 (Python Code)

Max Activating Token Index: 613

Text #3

Max Range: 2.1937. Min Range: -2.1937

Max Act: 2.1066. Min Act: -0.0000

Data Index: 1625911 (Python Code)

Max Activating Token Index: 521

Text #4

Max Range: 2.1937. Min Range: -2.1937

Max Act: 1.9733. Min Act: -0.0000

Data Index: 1643535 (Python Code)

Max Activating Token Index: 58

Text #5

Max Range: 2.1937. Min Range: -2.1937

Max Act: 1.9263. Min Act: -0.0000

Data Index: 1405003 (Python Code)

Max Activating Token Index: 552

Text #6

Max Range: 2.1937. Min Range: -2.1937

Max Act: 2.1774. Min Act: -0.0000

Data Index: 600849 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 2.1937. Min Range: -2.1937

Max Act: 1.8250. Min Act: -0.0000

Data Index: 1558526 (Python Code)

Max Activating Token Index: 354

Text #8

Max Range: 2.1937. Min Range: -2.1937

Max Act: 1.9148. Min Act: -0.0000

Data Index: 1481240 (Python Code)

Max Activating Token Index: 669

Text #9

Max Range: 2.1937. Min Range: -2.1937

Max Act: 1.8155. Min Act: -0.0000

Data Index: 396942 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 2.1937. Min Range: -2.1937

Max Act: 1.9121. Min Act: -0.0000

Data Index: 1404463 (Python Code)

Max Activating Token Index: 996

Text #11

Max Range: 2.1937. Min Range: -2.1937

Max Act: 1.7833. Min Act: -0.0000

Data Index: 297010 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 2.1937. Min Range: -2.1937

Max Act: 1.7891. Min Act: -0.0000

Data Index: 899003 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 2.1937. Min Range: -2.1937

Max Act: 1.7678. Min Act: -0.0000

Data Index: 221413 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 2.1937. Min Range: -2.1937

Max Act: 1.7431. Min Act: -0.0000

Data Index: 1615466 (Python Code)

Max Activating Token Index: 201

Text #15

Max Range: 2.1937. Min Range: -2.1937

Max Act: 1.7412. Min Act: -0.0000

Data Index: 1500394 (Python Code)

Max Activating Token Index: 166

Text #16

Max Range: 2.1937. Min Range: -2.1937

Max Act: 1.7198. Min Act: -0.0000

Data Index: 384231 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 2.1937. Min Range: -2.1937

Max Act: 1.7309. Min Act: -0.0000

Data Index: 1488868 (Python Code)

Max Activating Token Index: 28

Text #18

Max Range: 2.1937. Min Range: -2.1937

Max Act: 1.8182. Min Act: -0.0000

Data Index: 1593152 (Python Code)

Max Activating Token Index: 845

Text #19

Max Range: 2.1937. Min Range: -2.1937

Max Act: 1.8131. Min Act: -0.0000

Data Index: 1414893 (Python Code)

Max Activating Token Index: 1019