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

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

Neuron 960 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: 0.7396. Min Range: -0.7396

Max Act: 0.7272. Min Act: -0.0000

Data Index: 902317 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.7396. Min Act: -0.0000

Data Index: 735120 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.6488. Min Act: -0.0000

Data Index: 235405 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.6113. Min Act: -0.0000

Data Index: 1042712 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.5665. Min Act: -0.0000

Data Index: 460335 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.5838. Min Act: -0.0000

Data Index: 512792 (C4 (Web Text))

Max Activating Token Index: 810

Text #6

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.5726. Min Act: -0.0000

Data Index: 570115 (C4 (Web Text))

Max Activating Token Index: 572

Text #7

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.5600. Min Act: -0.0000

Data Index: 298206 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.5657. Min Act: -0.0000

Data Index: 1044149 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.5627. Min Act: -0.0000

Data Index: 583396 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.5588. Min Act: -0.0000

Data Index: 534058 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.5441. Min Act: -0.0000

Data Index: 954604 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.5060. Min Act: -0.0000

Data Index: 1059240 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.5167. Min Act: -0.0000

Data Index: 928371 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.5025. Min Act: -0.0000

Data Index: 617961 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.4982. Min Act: -0.0000

Data Index: 815007 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.5152. Min Act: -0.0000

Data Index: 45506 (C4 (Web Text))

Max Activating Token Index: 1005

Text #17

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.5124. Min Act: -0.0000

Data Index: 1359186 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.5061. Min Act: -0.0000

Data Index: 287118 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.4832. Min Act: -0.0000

Data Index: 217881 (C4 (Web Text))

Max Activating Token Index: 1002