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

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

Neuron 4660 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.8081. Min Act: -0.0000

Data Index: 26703 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.8016. Min Act: -0.0000

Data Index: 868150 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.7557. Min Act: -0.0000

Data Index: 1301943 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.7460. Min Act: -0.0000

Data Index: 923351 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.7525. Min Act: -0.0000

Data Index: 1024734 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.7265. Min Act: -0.0000

Data Index: 1266091 (C4 (Web Text))

Max Activating Token Index: 498

Text #6

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6626. Min Act: -0.0000

Data Index: 11579 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6992. Min Act: -0.0000

Data Index: 1123292 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6962. Min Act: -0.0000

Data Index: 482774 (C4 (Web Text))

Max Activating Token Index: 954

Text #9

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.7222. Min Act: -0.0000

Data Index: 398010 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6853. Min Act: -0.0000

Data Index: 1057967 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6272. Min Act: -0.0000

Data Index: 735426 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6885. Min Act: -0.0000

Data Index: 770677 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6899. Min Act: -0.0000

Data Index: 455818 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6603. Min Act: -0.0000

Data Index: 764507 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6380. Min Act: -0.0000

Data Index: 124349 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6212. Min Act: -0.0000

Data Index: 1334709 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6345. Min Act: -0.0000

Data Index: 453665 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.5819. Min Act: -0.0000

Data Index: 1049918 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.5891. Min Act: -0.0000

Data Index: 587966 (C4 (Web Text))

Max Activating Token Index: 447