Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 638 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2672. Min Act: -0.0000

Data Index: 1043368 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2501. Min Act: -0.0000

Data Index: 395649 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2124. Min Act: -0.0000

Data Index: 137078 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2103. Min Act: -0.0000

Data Index: 1179883 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2065. Min Act: -0.0000

Data Index: 978586 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.1934. Min Act: -0.0001

Data Index: 42984 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2045. Min Act: -0.0000

Data Index: 601020 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.1923. Min Act: -0.0001

Data Index: 353144 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.1937. Min Act: -0.0000

Data Index: 731684 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.1922. Min Act: -0.0000

Data Index: 1115546 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.1890. Min Act: 0.0000

Data Index: 253988 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.1777. Min Act: -0.0000

Data Index: 1000269 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.1925. Min Act: -0.0000

Data Index: 48402 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.1800. Min Act: -0.0001

Data Index: 550142 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.1841. Min Act: -0.0000

Data Index: 1355889 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.1827. Min Act: -0.0000

Data Index: 489736 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.1858. Min Act: -0.0001

Data Index: 860713 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.1751. Min Act: -0.0000

Data Index: 600579 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.1702. Min Act: -0.0001

Data Index: 60578 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.1790. Min Act: 0.0000

Data Index: 662891 (C4 (Web Text))

Max Activating Token Index: 834