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

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

Neuron 4727 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0923. Min Range: -1.0923

Max Act: 1.0923. Min Act: -0.0000

Data Index: 963330 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.7193. Min Act: -0.0000

Data Index: 37419 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.7830. Min Act: 0.0000

Data Index: 672660 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.7891. Min Act: -0.0000

Data Index: 1207568 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.7659. Min Act: -0.0000

Data Index: 1114001 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.7223. Min Act: -0.0000

Data Index: 1394873 (Python Code)

Max Activating Token Index: 540

Text #6

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.6916. Min Act: -0.0000

Data Index: 337159 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.6857. Min Act: -0.0000

Data Index: 762442 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.7034. Min Act: -0.0000

Data Index: 1593490 (Python Code)

Max Activating Token Index: 535

Text #9

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.6680. Min Act: -0.0000

Data Index: 919184 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.6579. Min Act: -0.0000

Data Index: 98102 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.6567. Min Act: -0.0000

Data Index: 1434753 (Python Code)

Max Activating Token Index: 249

Text #12

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.6394. Min Act: -0.0000

Data Index: 1497296 (Python Code)

Max Activating Token Index: 613

Text #13

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.6157. Min Act: -0.0000

Data Index: 1615356 (Python Code)

Max Activating Token Index: 667

Text #14

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.6666. Min Act: -0.0000

Data Index: 1458862 (Python Code)

Max Activating Token Index: 708

Text #15

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.6051. Min Act: -0.0000

Data Index: 1394449 (Python Code)

Max Activating Token Index: 533

Text #16

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.5859. Min Act: -0.0000

Data Index: 1290423 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.6049. Min Act: -0.0000

Data Index: 939380 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.6187. Min Act: -0.0000

Data Index: 1216680 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.6068. Min Act: -0.0000

Data Index: 1504628 (Python Code)

Max Activating Token Index: 978