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

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

Neuron 3314 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: 1.7811. Min Range: -1.7811

Max Act: 1.7811. Min Act: -0.0001

Data Index: 236912 (C4 (Web Text))

Max Activating Token Index: 234

Text #1

Max Range: 1.7811. Min Range: -1.7811

Max Act: 1.7068. Min Act: -0.0000

Data Index: 514097 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 1.7811. Min Range: -1.7811

Max Act: 1.5469. Min Act: -0.0001

Data Index: 1109867 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 1.7811. Min Range: -1.7811

Max Act: 1.1612. Min Act: -0.0000

Data Index: 846989 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 1.7811. Min Range: -1.7811

Max Act: 1.3130. Min Act: -0.0000

Data Index: 1282455 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 1.7811. Min Range: -1.7811

Max Act: 1.1721. Min Act: -0.0001

Data Index: 1036775 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 1.7811. Min Range: -1.7811

Max Act: 1.2332. Min Act: -0.0000

Data Index: 240219 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 1.7811. Min Range: -1.7811

Max Act: 1.1269. Min Act: -0.0000

Data Index: 598687 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 1.7811. Min Range: -1.7811

Max Act: 1.1652. Min Act: -0.0001

Data Index: 619351 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 1.7811. Min Range: -1.7811

Max Act: 1.0911. Min Act: -0.0000

Data Index: 551631 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 1.7811. Min Range: -1.7811

Max Act: 1.0449. Min Act: -0.0000

Data Index: 61313 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 1.7811. Min Range: -1.7811

Max Act: 0.9749. Min Act: -0.0001

Data Index: 542212 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 1.7811. Min Range: -1.7811

Max Act: 0.9956. Min Act: -0.0001

Data Index: 138756 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 1.7811. Min Range: -1.7811

Max Act: 0.9695. Min Act: -0.0000

Data Index: 1075976 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 1.7811. Min Range: -1.7811

Max Act: 0.9570. Min Act: -0.0000

Data Index: 106351 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 1.7811. Min Range: -1.7811

Max Act: 1.1344. Min Act: -0.0000

Data Index: 355244 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 1.7811. Min Range: -1.7811

Max Act: 0.9378. Min Act: -0.0000

Data Index: 994148 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 1.7811. Min Range: -1.7811

Max Act: 0.9501. Min Act: -0.0000

Data Index: 519454 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 1.7811. Min Range: -1.7811

Max Act: 0.9285. Min Act: -0.0000

Data Index: 696224 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 1.7811. Min Range: -1.7811

Max Act: 0.8083. Min Act: -0.0001

Data Index: 659763 (C4 (Web Text))

Max Activating Token Index: 244