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

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

Neuron 4305 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: 1.4517. Min Range: -1.4517

Max Act: 1.4517. Min Act: -0.0000

Data Index: 926538 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.3774. Min Act: -0.0000

Data Index: 214576 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.4301. Min Act: -0.0000

Data Index: 95128 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.3195. Min Act: -0.0000

Data Index: 80602 (C4 (Web Text))

Max Activating Token Index: 708

Text #4

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.3216. Min Act: -0.0000

Data Index: 1138352 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.2396. Min Act: -0.0000

Data Index: 458686 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.3556. Min Act: -0.0000

Data Index: 353594 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.2852. Min Act: 0.0000

Data Index: 487072 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.2821. Min Act: -0.0000

Data Index: 1097370 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.3525. Min Act: -0.0000

Data Index: 1084373 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.1123. Min Act: -0.0000

Data Index: 895980 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.3850. Min Act: -0.0000

Data Index: 292538 (C4 (Web Text))

Max Activating Token Index: 176

Text #12

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.2424. Min Act: -0.0000

Data Index: 445306 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.1370. Min Act: -0.0000

Data Index: 31033 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.2002. Min Act: -0.0000

Data Index: 161984 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.1890. Min Act: -0.0000

Data Index: 1140286 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.1996. Min Act: -0.0000

Data Index: 74326 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.0954. Min Act: -0.0000

Data Index: 924921 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.1612. Min Act: -0.0000

Data Index: 619468 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.1083. Min Act: -0.0000

Data Index: 276742 (C4 (Web Text))

Max Activating Token Index: 767