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

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

Neuron 1979 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: 1.2095. Min Range: -1.2095

Max Act: 1.2033. Min Act: -0.0000

Data Index: 97004 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 1.2095. Min Range: -1.2095

Max Act: 1.2095. Min Act: -0.0000

Data Index: 915348 (C4 (Web Text))

Max Activating Token Index: 408

Text #2

Max Range: 1.2095. Min Range: -1.2095

Max Act: 1.1921. Min Act: -0.0000

Data Index: 315692 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 1.2095. Min Range: -1.2095

Max Act: 1.0881. Min Act: -0.0000

Data Index: 975344 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 1.2095. Min Range: -1.2095

Max Act: 1.0777. Min Act: -0.0000

Data Index: 469732 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 1.2095. Min Range: -1.2095

Max Act: 1.1283. Min Act: -0.0000

Data Index: 102371 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 1.2095. Min Range: -1.2095

Max Act: 1.0845. Min Act: -0.0000

Data Index: 103097 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 1.2095. Min Range: -1.2095

Max Act: 1.0470. Min Act: -0.0000

Data Index: 1218833 (C4 (Web Text))

Max Activating Token Index: 516

Text #8

Max Range: 1.2095. Min Range: -1.2095

Max Act: 1.0370. Min Act: -0.0000

Data Index: 513678 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 1.2095. Min Range: -1.2095

Max Act: 1.0648. Min Act: -0.0000

Data Index: 270474 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 1.2095. Min Range: -1.2095

Max Act: 1.0265. Min Act: -0.0000

Data Index: 286399 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 1.2095. Min Range: -1.2095

Max Act: 0.9819. Min Act: -0.0000

Data Index: 522038 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 1.2095. Min Range: -1.2095

Max Act: 1.0300. Min Act: -0.0000

Data Index: 781615 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 1.2095. Min Range: -1.2095

Max Act: 0.9990. Min Act: -0.0000

Data Index: 644636 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 1.2095. Min Range: -1.2095

Max Act: 1.0055. Min Act: -0.0000

Data Index: 408940 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 1.2095. Min Range: -1.2095

Max Act: 0.9938. Min Act: -0.0000

Data Index: 501881 (C4 (Web Text))

Max Activating Token Index: 176

Text #16

Max Range: 1.2095. Min Range: -1.2095

Max Act: 0.9825. Min Act: -0.0000

Data Index: 583844 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 1.2095. Min Range: -1.2095

Max Act: 0.9823. Min Act: -0.0000

Data Index: 1340942 (C4 (Web Text))

Max Activating Token Index: 438

Text #18

Max Range: 1.2095. Min Range: -1.2095

Max Act: 0.9847. Min Act: -0.0000

Data Index: 933954 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 1.2095. Min Range: -1.2095

Max Act: 0.9858. Min Act: -0.0000

Data Index: 935345 (C4 (Web Text))

Max Activating Token Index: 646