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

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

Neuron 705 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0672. Min Act: -0.0002

Data Index: 70116 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0668. Min Act: -0.0002

Data Index: 674723 (C4 (Web Text))

Max Activating Token Index: 802

Text #2

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0636. Min Act: -0.0002

Data Index: 1261472 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0604. Min Act: -0.0002

Data Index: 1292860 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0584. Min Act: -0.0002

Data Index: 777938 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0581. Min Act: -0.0002

Data Index: 82073 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0574. Min Act: -0.0002

Data Index: 195095 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0567. Min Act: -0.0002

Data Index: 1360967 (Python Code)

Max Activating Token Index: 150

Text #8

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0566. Min Act: -0.0002

Data Index: 1209830 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0561. Min Act: -0.0002

Data Index: 1591574 (Python Code)

Max Activating Token Index: 742

Text #10

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0560. Min Act: -0.0002

Data Index: 1274088 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0559. Min Act: -0.0002

Data Index: 1046669 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0556. Min Act: -0.0002

Data Index: 350410 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0556. Min Act: -0.0002

Data Index: 575563 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0544. Min Act: -0.0002

Data Index: 757324 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0542. Min Act: -0.0002

Data Index: 181253 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1023010 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0528. Min Act: -0.0002

Data Index: 987319 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0525. Min Act: -0.0002

Data Index: 1297047 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0524. Min Act: -0.0002

Data Index: 961012 (C4 (Web Text))

Max Activating Token Index: 321