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

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

Neuron 4078 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7608. Min Range: -2.7608

Max Act: 2.7608. Min Act: -0.0001

Data Index: 521085 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 2.7608. Min Range: -2.7608

Max Act: 2.2921. Min Act: -0.0000

Data Index: 1302462 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 2.7608. Min Range: -2.7608

Max Act: 2.3725. Min Act: -0.0000

Data Index: 119386 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 2.7608. Min Range: -2.7608

Max Act: 2.1923. Min Act: -0.0000

Data Index: 732329 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 2.7608. Min Range: -2.7608

Max Act: 2.1816. Min Act: -0.0000

Data Index: 1131348 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 2.7608. Min Range: -2.7608

Max Act: 2.2827. Min Act: -0.0000

Data Index: 189473 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 2.7608. Min Range: -2.7608

Max Act: 2.1127. Min Act: -0.0000

Data Index: 924502 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 2.7608. Min Range: -2.7608

Max Act: 1.8702. Min Act: -0.0000

Data Index: 359238 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 2.7608. Min Range: -2.7608

Max Act: 1.9839. Min Act: -0.0001

Data Index: 874721 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 2.7608. Min Range: -2.7608

Max Act: 1.9557. Min Act: -0.0000

Data Index: 781539 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 2.7608. Min Range: -2.7608

Max Act: 1.5107. Min Act: -0.0001

Data Index: 713801 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 2.7608. Min Range: -2.7608

Max Act: 1.9675. Min Act: -0.0000

Data Index: 738461 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 2.7608. Min Range: -2.7608

Max Act: 1.9794. Min Act: -0.0000

Data Index: 1185576 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 2.7608. Min Range: -2.7608

Max Act: 1.9711. Min Act: -0.0001

Data Index: 931277 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 2.7608. Min Range: -2.7608

Max Act: 1.9166. Min Act: -0.0001

Data Index: 1307315 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 2.7608. Min Range: -2.7608

Max Act: 2.0441. Min Act: -0.0000

Data Index: 1315273 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 2.7608. Min Range: -2.7608

Max Act: 1.9207. Min Act: -0.0000

Data Index: 1077564 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 2.7608. Min Range: -2.7608

Max Act: 1.7752. Min Act: -0.0001

Data Index: 946352 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 2.7608. Min Range: -2.7608

Max Act: 1.7813. Min Act: -0.0000

Data Index: 1355010 (C4 (Web Text))

Max Activating Token Index: 331

Text #19

Max Range: 2.7608. Min Range: -2.7608

Max Act: 1.5906. Min Act: -0.0001

Data Index: 674291 (C4 (Web Text))

Max Activating Token Index: 426