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

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

Neuron 4642 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: 0.6057. Min Range: -0.6057

Max Act: 0.6057. Min Act: -0.0000

Data Index: 146447 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.5650. Min Act: -0.0000

Data Index: 1165708 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.5529. Min Act: -0.0000

Data Index: 420791 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.4476. Min Act: -0.0000

Data Index: 1139051 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.3838. Min Act: -0.0000

Data Index: 552344 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.3415. Min Act: -0.0000

Data Index: 49585 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.3476. Min Act: -0.0000

Data Index: 1281908 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.3189. Min Act: -0.0000

Data Index: 1295456 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.3289. Min Act: -0.0000

Data Index: 891667 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.3012. Min Act: -0.0000

Data Index: 1507568 (Python Code)

Max Activating Token Index: 914

Text #10

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.3117. Min Act: -0.0000

Data Index: 12525 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.3095. Min Act: -0.0000

Data Index: 1009303 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.3284. Min Act: -0.0000

Data Index: 1112170 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.3019. Min Act: -0.0000

Data Index: 719604 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.2802. Min Act: -0.0000

Data Index: 1375001 (Python Code)

Max Activating Token Index: 822

Text #15

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.2817. Min Act: -0.0000

Data Index: 1556376 (Python Code)

Max Activating Token Index: 571

Text #16

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.2611. Min Act: -0.0000

Data Index: 555519 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.2883. Min Act: -0.0000

Data Index: 19998 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.2830. Min Act: -0.0000

Data Index: 764776 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.2604. Min Act: -0.0000

Data Index: 884717 (C4 (Web Text))

Max Activating Token Index: 347