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

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

Neuron 127 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3258. Min Range: -1.3258

Max Act: 1.3258. Min Act: 0.0000

Data Index: 119860 (C4 (Web Text))

Max Activating Token Index: 344

Text #1

Max Range: 1.3258. Min Range: -1.3258

Max Act: 1.2592. Min Act: 0.0001

Data Index: 792046 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 1.3258. Min Range: -1.3258

Max Act: 1.1661. Min Act: -0.0000

Data Index: 1206603 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 1.3258. Min Range: -1.3258

Max Act: 1.1253. Min Act: -0.0000

Data Index: 721627 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 1.3258. Min Range: -1.3258

Max Act: 1.1095. Min Act: 0.0001

Data Index: 989178 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 1.3258. Min Range: -1.3258

Max Act: 1.1119. Min Act: 0.0000

Data Index: 1186969 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 1.3258. Min Range: -1.3258

Max Act: 1.1046. Min Act: -0.0000

Data Index: 813316 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 1.3258. Min Range: -1.3258

Max Act: 1.0980. Min Act: -0.0000

Data Index: 412723 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 1.3258. Min Range: -1.3258

Max Act: 1.1127. Min Act: -0.0000

Data Index: 570660 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 1.3258. Min Range: -1.3258

Max Act: 1.1036. Min Act: -0.0000

Data Index: 463743 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 1.3258. Min Range: -1.3258

Max Act: 1.0610. Min Act: -0.0000

Data Index: 871601 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 1.3258. Min Range: -1.3258

Max Act: 0.9479. Min Act: -0.0000

Data Index: 433888 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 1.3258. Min Range: -1.3258

Max Act: 0.9417. Min Act: -0.0000

Data Index: 181763 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 1.3258. Min Range: -1.3258

Max Act: 0.9456. Min Act: -0.0000

Data Index: 989431 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 1.3258. Min Range: -1.3258

Max Act: 0.9504. Min Act: 0.0000

Data Index: 569182 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 1.3258. Min Range: -1.3258

Max Act: 0.8558. Min Act: -0.0000

Data Index: 144602 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 1.3258. Min Range: -1.3258

Max Act: 0.9694. Min Act: -0.0000

Data Index: 1274143 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 1.3258. Min Range: -1.3258

Max Act: 0.8736. Min Act: 0.0000

Data Index: 124397 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 1.3258. Min Range: -1.3258

Max Act: 0.9952. Min Act: -0.0000

Data Index: 1266017 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 1.3258. Min Range: -1.3258

Max Act: 0.9322. Min Act: -0.0000

Data Index: 827164 (C4 (Web Text))

Max Activating Token Index: 171