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

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

Neuron 4296 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.7603. Min Act: -0.0000

Data Index: 20095 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.6929. Min Act: -0.0000

Data Index: 1577286 (Python Code)

Max Activating Token Index: 155

Text #2

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.5934. Min Act: -0.0000

Data Index: 1587813 (Python Code)

Max Activating Token Index: 430

Text #3

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.6070. Min Act: -0.0000

Data Index: 249783 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.5837. Min Act: -0.0000

Data Index: 1458071 (Python Code)

Max Activating Token Index: 840

Text #5

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.5708. Min Act: -0.0000

Data Index: 1533505 (Python Code)

Max Activating Token Index: 177

Text #6

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.5599. Min Act: -0.0000

Data Index: 566784 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.5295. Min Act: -0.0000

Data Index: 1587755 (Python Code)

Max Activating Token Index: 110

Text #8

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.5078. Min Act: -0.0000

Data Index: 1485827 (Python Code)

Max Activating Token Index: 66

Text #9

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.5258. Min Act: -0.0000

Data Index: 1433555 (Python Code)

Max Activating Token Index: 335

Text #10

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.5323. Min Act: -0.0000

Data Index: 1585425 (Python Code)

Max Activating Token Index: 243

Text #11

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.5380. Min Act: -0.0000

Data Index: 309650 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.5031. Min Act: -0.0000

Data Index: 1541319 (Python Code)

Max Activating Token Index: 41

Text #13

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.5359. Min Act: -0.0000

Data Index: 1413211 (Python Code)

Max Activating Token Index: 91

Text #14

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.5192. Min Act: -0.0000

Data Index: 1518685 (Python Code)

Max Activating Token Index: 404

Text #15

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.4930. Min Act: -0.0000

Data Index: 854009 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.5015. Min Act: -0.0000

Data Index: 1505181 (Python Code)

Max Activating Token Index: 789

Text #17

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.4811. Min Act: -0.0000

Data Index: 1552657 (Python Code)

Max Activating Token Index: 72

Text #18

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.4312. Min Act: -0.0000

Data Index: 299928 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.4862. Min Act: -0.0000

Data Index: 1419365 (Python Code)

Max Activating Token Index: 934