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

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

Neuron 840 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6261. Min Range: -1.6261

Max Act: 1.6261. Min Act: -0.0000

Data Index: 903423 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 1.6261. Min Range: -1.6261

Max Act: 1.6060. Min Act: -0.0000

Data Index: 1594067 (Python Code)

Max Activating Token Index: 218

Text #2

Max Range: 1.6261. Min Range: -1.6261

Max Act: 1.5411. Min Act: -0.0000

Data Index: 855844 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 1.6261. Min Range: -1.6261

Max Act: 1.2644. Min Act: -0.0000

Data Index: 104409 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 1.6261. Min Range: -1.6261

Max Act: 1.1686. Min Act: -0.0000

Data Index: 36686 (C4 (Web Text))

Max Activating Token Index: 731

Text #5

Max Range: 1.6261. Min Range: -1.6261

Max Act: 1.2280. Min Act: -0.0000

Data Index: 700303 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 1.6261. Min Range: -1.6261

Max Act: 1.1891. Min Act: -0.0000

Data Index: 651220 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 1.6261. Min Range: -1.6261

Max Act: 1.2201. Min Act: -0.0000

Data Index: 1175823 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 1.6261. Min Range: -1.6261

Max Act: 1.2522. Min Act: -0.0000

Data Index: 272358 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 1.6261. Min Range: -1.6261

Max Act: 1.1863. Min Act: -0.0000

Data Index: 572953 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 1.6261. Min Range: -1.6261

Max Act: 1.0896. Min Act: -0.0000

Data Index: 723991 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 1.6261. Min Range: -1.6261

Max Act: 1.2346. Min Act: -0.0000

Data Index: 404978 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 1.6261. Min Range: -1.6261

Max Act: 1.0558. Min Act: -0.0000

Data Index: 642839 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 1.6261. Min Range: -1.6261

Max Act: 1.3049. Min Act: -0.0000

Data Index: 689148 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 1.6261. Min Range: -1.6261

Max Act: 1.1095. Min Act: -0.0000

Data Index: 66070 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 1.6261. Min Range: -1.6261

Max Act: 1.1044. Min Act: -0.0000

Data Index: 966451 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 1.6261. Min Range: -1.6261

Max Act: 0.9551. Min Act: -0.0000

Data Index: 622062 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 1.6261. Min Range: -1.6261

Max Act: 1.1433. Min Act: -0.0000

Data Index: 669827 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 1.6261. Min Range: -1.6261

Max Act: 1.0757. Min Act: -0.0000

Data Index: 372682 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 1.6261. Min Range: -1.6261

Max Act: 1.0116. Min Act: -0.0000

Data Index: 1188959 (C4 (Web Text))

Max Activating Token Index: 80