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

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

Neuron 2110 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: 1.3565. Min Range: -1.3565

Max Act: 1.3565. Min Act: -0.0000

Data Index: 1146473 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 1.3565. Min Range: -1.3565

Max Act: 0.8784. Min Act: -0.0000

Data Index: 470487 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 1.3565. Min Range: -1.3565

Max Act: 0.9000. Min Act: -0.0000

Data Index: 1336335 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 1.3565. Min Range: -1.3565

Max Act: 0.8827. Min Act: -0.0000

Data Index: 459888 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 1.3565. Min Range: -1.3565

Max Act: 0.8056. Min Act: -0.0000

Data Index: 786652 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 1.3565. Min Range: -1.3565

Max Act: 0.8356. Min Act: -0.0000

Data Index: 330901 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 1.3565. Min Range: -1.3565

Max Act: 0.7747. Min Act: -0.0000

Data Index: 862152 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 1.3565. Min Range: -1.3565

Max Act: 0.7762. Min Act: -0.0000

Data Index: 323416 (C4 (Web Text))

Max Activating Token Index: 744

Text #8

Max Range: 1.3565. Min Range: -1.3565

Max Act: 0.7893. Min Act: -0.0000

Data Index: 890577 (C4 (Web Text))

Max Activating Token Index: 546

Text #9

Max Range: 1.3565. Min Range: -1.3565

Max Act: 0.8096. Min Act: -0.0000

Data Index: 234142 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 1.3565. Min Range: -1.3565

Max Act: 0.7592. Min Act: 0.0000

Data Index: 218525 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 1.3565. Min Range: -1.3565

Max Act: 0.7579. Min Act: 0.0000

Data Index: 1046435 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 1.3565. Min Range: -1.3565

Max Act: 0.7284. Min Act: 0.0000

Data Index: 21453 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 1.3565. Min Range: -1.3565

Max Act: 0.7509. Min Act: -0.0000

Data Index: 17663 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 1.3565. Min Range: -1.3565

Max Act: 0.7594. Min Act: -0.0000

Data Index: 785376 (C4 (Web Text))

Max Activating Token Index: 958

Text #15

Max Range: 1.3565. Min Range: -1.3565

Max Act: 0.7525. Min Act: -0.0000

Data Index: 784787 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 1.3565. Min Range: -1.3565

Max Act: 0.6845. Min Act: 0.0000

Data Index: 202952 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 1.3565. Min Range: -1.3565

Max Act: 0.7471. Min Act: 0.0000

Data Index: 334747 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 1.3565. Min Range: -1.3565

Max Act: 0.7323. Min Act: -0.0000

Data Index: 201057 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 1.3565. Min Range: -1.3565

Max Act: 0.7805. Min Act: 0.0000

Data Index: 348328 (C4 (Web Text))

Max Activating Token Index: 198