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

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

Neuron 3970 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.2140. Min Act: -0.0001

Data Index: 1421473 (Python Code)

Max Activating Token Index: 560

Text #1

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.2090. Min Act: -0.0001

Data Index: 1514348 (Python Code)

Max Activating Token Index: 281

Text #2

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.2198. Min Act: -0.0001

Data Index: 1481302 (Python Code)

Max Activating Token Index: 403

Text #3

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1936. Min Act: -0.0001

Data Index: 1547308 (Python Code)

Max Activating Token Index: 639

Text #4

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1958. Min Act: -0.0001

Data Index: 1509753 (Python Code)

Max Activating Token Index: 666

Text #5

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1981. Min Act: -0.0001

Data Index: 1574372 (Python Code)

Max Activating Token Index: 907

Text #6

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.2132. Min Act: -0.0001

Data Index: 1496021 (Python Code)

Max Activating Token Index: 99

Text #7

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1944. Min Act: -0.0001

Data Index: 1468598 (Python Code)

Max Activating Token Index: 481

Text #8

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1939. Min Act: -0.0001

Data Index: 1581835 (Python Code)

Max Activating Token Index: 978

Text #9

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1915. Min Act: -0.0001

Data Index: 1405533 (Python Code)

Max Activating Token Index: 978

Text #10

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1887. Min Act: -0.0001

Data Index: 1547084 (Python Code)

Max Activating Token Index: 492

Text #11

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1815. Min Act: -0.0001

Data Index: 1426508 (Python Code)

Max Activating Token Index: 499

Text #12

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1791. Min Act: -0.0001

Data Index: 1538614 (Python Code)

Max Activating Token Index: 658

Text #13

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1859. Min Act: -0.0001

Data Index: 1613320 (Python Code)

Max Activating Token Index: 506

Text #14

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1781. Min Act: -0.0001

Data Index: 1410916 (Python Code)

Max Activating Token Index: 601

Text #15

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1955. Min Act: -0.0001

Data Index: 1514951 (Python Code)

Max Activating Token Index: 56

Text #16

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1770. Min Act: -0.0001

Data Index: 1516923 (Python Code)

Max Activating Token Index: 288

Text #17

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1744. Min Act: -0.0001

Data Index: 1625034 (Python Code)

Max Activating Token Index: 721

Text #18

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1872. Min Act: -0.0001

Data Index: 1569498 (Python Code)

Max Activating Token Index: 256

Text #19

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1894. Min Act: -0.0001

Data Index: 1453443 (Python Code)

Max Activating Token Index: 952