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

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

Neuron 652 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1284. Min Act: -0.0001

Data Index: 1248866 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1161. Min Act: -0.0001

Data Index: 350359 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1103. Min Act: -0.0001

Data Index: 1238426 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1188. Min Act: -0.0001

Data Index: 100236 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0984. Min Act: -0.0001

Data Index: 1342885 (C4 (Web Text))

Max Activating Token Index: 476

Text #5

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1013. Min Act: -0.0001

Data Index: 78251 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0875. Min Act: -0.0001

Data Index: 956531 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1010. Min Act: -0.0001

Data Index: 352988 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0937. Min Act: -0.0001

Data Index: 1044993 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0844. Min Act: -0.0001

Data Index: 341947 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1097. Min Act: -0.0001

Data Index: 792371 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0990. Min Act: -0.0001

Data Index: 837949 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0940. Min Act: -0.0001

Data Index: 944513 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0931. Min Act: -0.0001

Data Index: 446964 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1002. Min Act: -0.0001

Data Index: 890717 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1066. Min Act: -0.0001

Data Index: 152902 (C4 (Web Text))

Max Activating Token Index: 732

Text #16

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0895. Min Act: -0.0001

Data Index: 199649 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1064. Min Act: -0.0001

Data Index: 83793 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0884. Min Act: -0.0001

Data Index: 407551 (C4 (Web Text))

Max Activating Token Index: 269

Text #19

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1012. Min Act: -0.0001

Data Index: 527536 (C4 (Web Text))

Max Activating Token Index: 617