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

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

Neuron 2294 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.8907. Min Range: -7.8907

Max Act: 7.8907. Min Act: -0.0000

Data Index: 1388240 (Python Code)

Max Activating Token Index: 409

Text #1

Max Range: 7.8907. Min Range: -7.8907

Max Act: 7.0387. Min Act: -0.0000

Data Index: 1583159 (Python Code)

Max Activating Token Index: 117

Text #2

Max Range: 7.8907. Min Range: -7.8907

Max Act: 6.9391. Min Act: -0.0000

Data Index: 1602673 (Python Code)

Max Activating Token Index: 165

Text #3

Max Range: 7.8907. Min Range: -7.8907

Max Act: 6.7878. Min Act: -0.0000

Data Index: 1632810 (Python Code)

Max Activating Token Index: 431

Text #4

Max Range: 7.8907. Min Range: -7.8907

Max Act: 6.6329. Min Act: -0.0000

Data Index: 1552949 (Python Code)

Max Activating Token Index: 217

Text #5

Max Range: 7.8907. Min Range: -7.8907

Max Act: 6.5958. Min Act: -0.0000

Data Index: 1539881 (Python Code)

Max Activating Token Index: 629

Text #6

Max Range: 7.8907. Min Range: -7.8907

Max Act: 6.3965. Min Act: -0.0000

Data Index: 1613362 (Python Code)

Max Activating Token Index: 40

Text #7

Max Range: 7.8907. Min Range: -7.8907

Max Act: 6.7175. Min Act: -0.0000

Data Index: 1554723 (Python Code)

Max Activating Token Index: 825

Text #8

Max Range: 7.8907. Min Range: -7.8907

Max Act: 6.4833. Min Act: -0.0000

Data Index: 1443788 (Python Code)

Max Activating Token Index: 671

Text #9

Max Range: 7.8907. Min Range: -7.8907

Max Act: 6.3025. Min Act: -0.0000

Data Index: 1494495 (Python Code)

Max Activating Token Index: 523

Text #10

Max Range: 7.8907. Min Range: -7.8907

Max Act: 6.1060. Min Act: -0.0000

Data Index: 1459249 (Python Code)

Max Activating Token Index: 757

Text #11

Max Range: 7.8907. Min Range: -7.8907

Max Act: 6.6276. Min Act: -0.0000

Data Index: 1400982 (Python Code)

Max Activating Token Index: 379

Text #12

Max Range: 7.8907. Min Range: -7.8907

Max Act: 6.4536. Min Act: -0.0000

Data Index: 1528154 (Python Code)

Max Activating Token Index: 747

Text #13

Max Range: 7.8907. Min Range: -7.8907

Max Act: 6.4216. Min Act: -0.0000

Data Index: 1526823 (Python Code)

Max Activating Token Index: 168

Text #14

Max Range: 7.8907. Min Range: -7.8907

Max Act: 6.3470. Min Act: -0.0000

Data Index: 1631800 (Python Code)

Max Activating Token Index: 858

Text #15

Max Range: 7.8907. Min Range: -7.8907

Max Act: 6.1469. Min Act: -0.0000

Data Index: 1539862 (Python Code)

Max Activating Token Index: 30

Text #16

Max Range: 7.8907. Min Range: -7.8907

Max Act: 6.3247. Min Act: -0.0000

Data Index: 1449883 (Python Code)

Max Activating Token Index: 610

Text #17

Max Range: 7.8907. Min Range: -7.8907

Max Act: 6.3085. Min Act: -0.0000

Data Index: 1575342 (Python Code)

Max Activating Token Index: 452

Text #18

Max Range: 7.8907. Min Range: -7.8907

Max Act: 6.3069. Min Act: -0.0000

Data Index: 1532072 (Python Code)

Max Activating Token Index: 64

Text #19

Max Range: 7.8907. Min Range: -7.8907

Max Act: 6.2929. Min Act: -0.0000

Data Index: 1618377 (Python Code)

Max Activating Token Index: 974