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

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

Neuron 5086 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0073. Min Act: -0.0002

Data Index: 297381 (C4 (Web Text))

Max Activating Token Index: 403

Text #1

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0070. Min Act: -0.0002

Data Index: 1049190 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0063. Min Act: -0.0002

Data Index: 394438 (C4 (Web Text))

Max Activating Token Index: 309

Text #3

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0070. Min Act: -0.0002

Data Index: 390842 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0066. Min Act: -0.0002

Data Index: 634414 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0069. Min Act: -0.0002

Data Index: 792984 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0069. Min Act: -0.0002

Data Index: 584525 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0066. Min Act: -0.0002

Data Index: 738986 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0062. Min Act: -0.0002

Data Index: 702201 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0067. Min Act: -0.0002

Data Index: 683634 (C4 (Web Text))

Max Activating Token Index: 277

Text #10

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0063. Min Act: -0.0002

Data Index: 1264119 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0060. Min Act: -0.0002

Data Index: 210604 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0064. Min Act: -0.0002

Data Index: 1048666 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0056. Min Act: -0.0002

Data Index: 539635 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0063. Min Act: -0.0002

Data Index: 717959 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0058. Min Act: -0.0002

Data Index: 212527 (C4 (Web Text))

Max Activating Token Index: 480

Text #16

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0057. Min Act: -0.0002

Data Index: 248465 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0051. Min Act: -0.0002

Data Index: 971503 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0056. Min Act: -0.0002

Data Index: 916295 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0057. Min Act: -0.0002

Data Index: 1205084 (C4 (Web Text))

Max Activating Token Index: 303