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

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

Neuron 5693 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2135. Min Range: -1.2135

Max Act: 1.2135. Min Act: -0.0000

Data Index: 1420895 (Python Code)

Max Activating Token Index: 920

Text #1

Max Range: 1.2135. Min Range: -1.2135

Max Act: 1.0670. Min Act: -0.0000

Data Index: 1380837 (Python Code)

Max Activating Token Index: 353

Text #2

Max Range: 1.2135. Min Range: -1.2135

Max Act: 1.0255. Min Act: -0.0000

Data Index: 1643579 (Python Code)

Max Activating Token Index: 431

Text #3

Max Range: 1.2135. Min Range: -1.2135

Max Act: 0.9574. Min Act: -0.0000

Data Index: 1469882 (Python Code)

Max Activating Token Index: 571

Text #4

Max Range: 1.2135. Min Range: -1.2135

Max Act: 0.9507. Min Act: -0.0000

Data Index: 1375776 (Python Code)

Max Activating Token Index: 638

Text #5

Max Range: 1.2135. Min Range: -1.2135

Max Act: 0.9467. Min Act: -0.0000

Data Index: 1514142 (Python Code)

Max Activating Token Index: 438

Text #6

Max Range: 1.2135. Min Range: -1.2135

Max Act: 0.8765. Min Act: -0.0000

Data Index: 1391766 (Python Code)

Max Activating Token Index: 532

Text #7

Max Range: 1.2135. Min Range: -1.2135

Max Act: 0.9133. Min Act: -0.0000

Data Index: 1466996 (Python Code)

Max Activating Token Index: 741

Text #8

Max Range: 1.2135. Min Range: -1.2135

Max Act: 0.8094. Min Act: -0.0000

Data Index: 1544959 (Python Code)

Max Activating Token Index: 910

Text #9

Max Range: 1.2135. Min Range: -1.2135

Max Act: 0.7886. Min Act: -0.0000

Data Index: 1447003 (Python Code)

Max Activating Token Index: 627

Text #10

Max Range: 1.2135. Min Range: -1.2135

Max Act: 0.8263. Min Act: -0.0000

Data Index: 1591598 (Python Code)

Max Activating Token Index: 816

Text #11

Max Range: 1.2135. Min Range: -1.2135

Max Act: 0.8008. Min Act: -0.0000

Data Index: 1598214 (Python Code)

Max Activating Token Index: 160

Text #12

Max Range: 1.2135. Min Range: -1.2135

Max Act: 0.8473. Min Act: -0.0000

Data Index: 1499825 (Python Code)

Max Activating Token Index: 213

Text #13

Max Range: 1.2135. Min Range: -1.2135

Max Act: 0.8138. Min Act: -0.0000

Data Index: 1405681 (Python Code)

Max Activating Token Index: 888

Text #14

Max Range: 1.2135. Min Range: -1.2135

Max Act: 0.8196. Min Act: -0.0000

Data Index: 1415391 (Python Code)

Max Activating Token Index: 695

Text #15

Max Range: 1.2135. Min Range: -1.2135

Max Act: 0.8190. Min Act: -0.0000

Data Index: 1558863 (Python Code)

Max Activating Token Index: 995

Text #16

Max Range: 1.2135. Min Range: -1.2135

Max Act: 0.8014. Min Act: -0.0000

Data Index: 1530543 (Python Code)

Max Activating Token Index: 366

Text #17

Max Range: 1.2135. Min Range: -1.2135

Max Act: 0.7816. Min Act: -0.0000

Data Index: 1570925 (Python Code)

Max Activating Token Index: 91

Text #18

Max Range: 1.2135. Min Range: -1.2135

Max Act: 0.7597. Min Act: -0.0000

Data Index: 1588431 (Python Code)

Max Activating Token Index: 260

Text #19

Max Range: 1.2135. Min Range: -1.2135

Max Act: 0.7250. Min Act: -0.0000

Data Index: 1563252 (Python Code)

Max Activating Token Index: 909