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

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

Neuron 1205 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: 0.8824. Min Range: -0.8824

Max Act: 0.8824. Min Act: -0.0000

Data Index: 1520271 (Python Code)

Max Activating Token Index: 423

Text #1

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.8389. Min Act: -0.0000

Data Index: 1484426 (Python Code)

Max Activating Token Index: 167

Text #2

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.8030. Min Act: -0.0001

Data Index: 1587242 (Python Code)

Max Activating Token Index: 758

Text #3

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.7742. Min Act: -0.0001

Data Index: 1452111 (Python Code)

Max Activating Token Index: 600

Text #4

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.7754. Min Act: -0.0001

Data Index: 1420555 (Python Code)

Max Activating Token Index: 288

Text #5

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.7755. Min Act: -0.0001

Data Index: 1394072 (Python Code)

Max Activating Token Index: 217

Text #6

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.8039. Min Act: -0.0001

Data Index: 1653794 (Python Code)

Max Activating Token Index: 828

Text #7

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.7949. Min Act: -0.0000

Data Index: 1446965 (Python Code)

Max Activating Token Index: 868

Text #8

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.7635. Min Act: -0.0001

Data Index: 1590034 (Python Code)

Max Activating Token Index: 449

Text #9

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.7438. Min Act: -0.0001

Data Index: 1583810 (Python Code)

Max Activating Token Index: 837

Text #10

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.7446. Min Act: -0.0001

Data Index: 1462032 (Python Code)

Max Activating Token Index: 59

Text #11

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.7207. Min Act: -0.0001

Data Index: 1385204 (Python Code)

Max Activating Token Index: 851

Text #12

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.7537. Min Act: -0.0000

Data Index: 1533862 (Python Code)

Max Activating Token Index: 884

Text #13

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.7090. Min Act: -0.0000

Data Index: 1371401 (Python Code)

Max Activating Token Index: 296

Text #14

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.7303. Min Act: -0.0001

Data Index: 1629340 (Python Code)

Max Activating Token Index: 128

Text #15

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.7298. Min Act: -0.0001

Data Index: 1484211 (Python Code)

Max Activating Token Index: 868

Text #16

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.7244. Min Act: -0.0001

Data Index: 1575218 (Python Code)

Max Activating Token Index: 224

Text #17

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.7164. Min Act: -0.0001

Data Index: 1527348 (Python Code)

Max Activating Token Index: 315

Text #18

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.6725. Min Act: -0.0000

Data Index: 1641106 (Python Code)

Max Activating Token Index: 179

Text #19

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.6906. Min Act: -0.0000

Data Index: 1526044 (Python Code)

Max Activating Token Index: 780