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

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

Neuron 3746 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6923. Min Range: -2.6923

Max Act: 2.6923. Min Act: -0.0000

Data Index: 1601707 (Python Code)

Max Activating Token Index: 1002

Text #1

Max Range: 2.6923. Min Range: -2.6923

Max Act: 2.5589. Min Act: -0.0000

Data Index: 1522488 (Python Code)

Max Activating Token Index: 961

Text #2

Max Range: 2.6923. Min Range: -2.6923

Max Act: 2.5993. Min Act: -0.0000

Data Index: 1585858 (Python Code)

Max Activating Token Index: 883

Text #3

Max Range: 2.6923. Min Range: -2.6923

Max Act: 2.4364. Min Act: -0.0000

Data Index: 1656830 (Python Code)

Max Activating Token Index: 178

Text #4

Max Range: 2.6923. Min Range: -2.6923

Max Act: 2.0964. Min Act: -0.0000

Data Index: 1574708 (Python Code)

Max Activating Token Index: 797

Text #5

Max Range: 2.6923. Min Range: -2.6923

Max Act: 2.0009. Min Act: -0.0000

Data Index: 1562411 (Python Code)

Max Activating Token Index: 168

Text #6

Max Range: 2.6923. Min Range: -2.6923

Max Act: 2.1094. Min Act: -0.0000

Data Index: 1646135 (Python Code)

Max Activating Token Index: 172

Text #7

Max Range: 2.6923. Min Range: -2.6923

Max Act: 1.9436. Min Act: -0.0000

Data Index: 1646076 (Python Code)

Max Activating Token Index: 944

Text #8

Max Range: 2.6923. Min Range: -2.6923

Max Act: 2.1712. Min Act: -0.0000

Data Index: 1607548 (Python Code)

Max Activating Token Index: 68

Text #9

Max Range: 2.6923. Min Range: -2.6923

Max Act: 2.0606. Min Act: -0.0000

Data Index: 1370974 (Python Code)

Max Activating Token Index: 46

Text #10

Max Range: 2.6923. Min Range: -2.6923

Max Act: 2.2496. Min Act: -0.0000

Data Index: 1646977 (Python Code)

Max Activating Token Index: 584

Text #11

Max Range: 2.6923. Min Range: -2.6923

Max Act: 2.2648. Min Act: -0.0000

Data Index: 1431113 (Python Code)

Max Activating Token Index: 477

Text #12

Max Range: 2.6923. Min Range: -2.6923

Max Act: 1.9697. Min Act: -0.0000

Data Index: 1447826 (Python Code)

Max Activating Token Index: 143

Text #13

Max Range: 2.6923. Min Range: -2.6923

Max Act: 1.9187. Min Act: -0.0000

Data Index: 1557344 (Python Code)

Max Activating Token Index: 1011

Text #14

Max Range: 2.6923. Min Range: -2.6923

Max Act: 1.9987. Min Act: -0.0000

Data Index: 1643924 (Python Code)

Max Activating Token Index: 443

Text #15

Max Range: 2.6923. Min Range: -2.6923

Max Act: 1.8654. Min Act: -0.0000

Data Index: 1533185 (Python Code)

Max Activating Token Index: 39

Text #16

Max Range: 2.6923. Min Range: -2.6923

Max Act: 1.7935. Min Act: -0.0000

Data Index: 1534120 (Python Code)

Max Activating Token Index: 44

Text #17

Max Range: 2.6923. Min Range: -2.6923

Max Act: 1.9420. Min Act: -0.0000

Data Index: 1542262 (Python Code)

Max Activating Token Index: 43

Text #18

Max Range: 2.6923. Min Range: -2.6923

Max Act: 1.8428. Min Act: -0.0000

Data Index: 1595419 (Python Code)

Max Activating Token Index: 81

Text #19

Max Range: 2.6923. Min Range: -2.6923

Max Act: 1.7927. Min Act: -0.0000

Data Index: 1576356 (Python Code)

Max Activating Token Index: 97