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

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

Neuron 2653 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.9615. Min Act: -0.0002

Data Index: 1122798 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.9517. Min Act: -0.0002

Data Index: 766301 (C4 (Web Text))

Max Activating Token Index: 601

Text #2

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.9097. Min Act: -0.0002

Data Index: 84955 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.9105. Min Act: -0.0002

Data Index: 209520 (C4 (Web Text))

Max Activating Token Index: 779

Text #4

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.8918. Min Act: -0.0002

Data Index: 803295 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.8791. Min Act: -0.0002

Data Index: 266617 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.8773. Min Act: -0.0002

Data Index: 638252 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.8558. Min Act: -0.0003

Data Index: 869960 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.8328. Min Act: -0.0002

Data Index: 1091758 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.8412. Min Act: -0.0002

Data Index: 516372 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.8465. Min Act: -0.0002

Data Index: 386526 (C4 (Web Text))

Max Activating Token Index: 697

Text #11

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.8433. Min Act: -0.0002

Data Index: 483104 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.8290. Min Act: -0.0002

Data Index: 296907 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.8038. Min Act: -0.0002

Data Index: 1336455 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.8050. Min Act: -0.0002

Data Index: 525647 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.7900. Min Act: -0.0003

Data Index: 623037 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.7874. Min Act: -0.0002

Data Index: 1310267 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.7933. Min Act: -0.0003

Data Index: 553555 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.7941. Min Act: -0.0002

Data Index: 1242278 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.7672. Min Act: -0.0002

Data Index: 1263493 (C4 (Web Text))

Max Activating Token Index: 393