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

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

Neuron 3986 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6117. Min Range: -1.6117

Max Act: 1.6117. Min Act: -0.0002

Data Index: 1541164 (Python Code)

Max Activating Token Index: 22

Text #1

Max Range: 1.6117. Min Range: -1.6117

Max Act: 1.4144. Min Act: -0.0002

Data Index: 1468414 (Python Code)

Max Activating Token Index: 748

Text #2

Max Range: 1.6117. Min Range: -1.6117

Max Act: 1.4858. Min Act: -0.0002

Data Index: 1407774 (Python Code)

Max Activating Token Index: 667

Text #3

Max Range: 1.6117. Min Range: -1.6117

Max Act: 1.5042. Min Act: -0.0002

Data Index: 1511428 (Python Code)

Max Activating Token Index: 41

Text #4

Max Range: 1.6117. Min Range: -1.6117

Max Act: 1.5876. Min Act: -0.0002

Data Index: 1481418 (Python Code)

Max Activating Token Index: 95

Text #5

Max Range: 1.6117. Min Range: -1.6117

Max Act: 1.4763. Min Act: -0.0002

Data Index: 1628397 (Python Code)

Max Activating Token Index: 896

Text #6

Max Range: 1.6117. Min Range: -1.6117

Max Act: 1.4420. Min Act: -0.0002

Data Index: 1539485 (Python Code)

Max Activating Token Index: 264

Text #7

Max Range: 1.6117. Min Range: -1.6117

Max Act: 1.2195. Min Act: -0.0002

Data Index: 1655215 (Python Code)

Max Activating Token Index: 785

Text #8

Max Range: 1.6117. Min Range: -1.6117

Max Act: 1.5748. Min Act: -0.0002

Data Index: 1566961 (Python Code)

Max Activating Token Index: 209

Text #9

Max Range: 1.6117. Min Range: -1.6117

Max Act: 1.3609. Min Act: -0.0002

Data Index: 1398849 (Python Code)

Max Activating Token Index: 568

Text #10

Max Range: 1.6117. Min Range: -1.6117

Max Act: 1.3601. Min Act: -0.0002

Data Index: 1483378 (Python Code)

Max Activating Token Index: 940

Text #11

Max Range: 1.6117. Min Range: -1.6117

Max Act: 1.3114. Min Act: -0.0002

Data Index: 1431277 (Python Code)

Max Activating Token Index: 118

Text #12

Max Range: 1.6117. Min Range: -1.6117

Max Act: 1.3885. Min Act: -0.0002

Data Index: 1607535 (Python Code)

Max Activating Token Index: 540

Text #13

Max Range: 1.6117. Min Range: -1.6117

Max Act: 1.2637. Min Act: -0.0002

Data Index: 1616826 (Python Code)

Max Activating Token Index: 399

Text #14

Max Range: 1.6117. Min Range: -1.6117

Max Act: 1.3225. Min Act: -0.0002

Data Index: 1437515 (Python Code)

Max Activating Token Index: 463

Text #15

Max Range: 1.6117. Min Range: -1.6117

Max Act: 1.2732. Min Act: -0.0002

Data Index: 1408959 (Python Code)

Max Activating Token Index: 491

Text #16

Max Range: 1.6117. Min Range: -1.6117

Max Act: 1.3549. Min Act: -0.0002

Data Index: 1638675 (Python Code)

Max Activating Token Index: 271

Text #17

Max Range: 1.6117. Min Range: -1.6117

Max Act: 1.1190. Min Act: -0.0002

Data Index: 1492937 (Python Code)

Max Activating Token Index: 542

Text #18

Max Range: 1.6117. Min Range: -1.6117

Max Act: 1.3591. Min Act: -0.0002

Data Index: 1408397 (Python Code)

Max Activating Token Index: 988

Text #19

Max Range: 1.6117. Min Range: -1.6117

Max Act: 1.2759. Min Act: -0.0002

Data Index: 1538323 (Python Code)

Max Activating Token Index: 750