Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1834 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.5001. Min Range: -5.5001

Max Act: 5.5001. Min Act: -0.1700

Data Index: 633091 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 5.5001. Min Range: -5.5001

Max Act: 5.5001. Min Act: -0.1700

Data Index: 284959 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 5.5001. Min Range: -5.5001

Max Act: 5.3126. Min Act: -0.1700

Data Index: 944270 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 5.5001. Min Range: -5.5001

Max Act: 5.2501. Min Act: -0.1699

Data Index: 38869 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 5.5001. Min Range: -5.5001

Max Act: 5.2188. Min Act: -0.1700

Data Index: 187989 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 5.5001. Min Range: -5.5001

Max Act: 5.1876. Min Act: -0.1700

Data Index: 416602 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 5.5001. Min Range: -5.5001

Max Act: 5.1251. Min Act: -0.1700

Data Index: 1050430 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 5.5001. Min Range: -5.5001

Max Act: 5.0938. Min Act: -0.1700

Data Index: 549173 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 5.5001. Min Range: -5.5001

Max Act: 5.0938. Min Act: -0.1699

Data Index: 17496 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 5.5001. Min Range: -5.5001

Max Act: 5.0938. Min Act: -0.1700

Data Index: 868149 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 5.5001. Min Range: -5.5001

Max Act: 5.1563. Min Act: -0.1699

Data Index: 509301 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 5.5001. Min Range: -5.5001

Max Act: 5.0626. Min Act: -0.1700

Data Index: 971577 (C4 (Web Text))

Max Activating Token Index: 557

Text #12

Max Range: 5.5001. Min Range: -5.5001

Max Act: 5.0938. Min Act: -0.1700

Data Index: 1352904 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 5.5001. Min Range: -5.5001

Max Act: 5.0938. Min Act: -0.1700

Data Index: 357923 (C4 (Web Text))

Max Activating Token Index: 587

Text #14

Max Range: 5.5001. Min Range: -5.5001

Max Act: 5.0001. Min Act: -0.1700

Data Index: 583592 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 5.5001. Min Range: -5.5001

Max Act: 5.0938. Min Act: -0.1700

Data Index: 78509 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 5.5001. Min Range: -5.5001

Max Act: 5.0938. Min Act: -0.1700

Data Index: 657373 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 5.5001. Min Range: -5.5001

Max Act: 5.0313. Min Act: -0.1700

Data Index: 1007620 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 5.5001. Min Range: -5.5001

Max Act: 5.0626. Min Act: -0.1699

Data Index: 649694 (C4 (Web Text))

Max Activating Token Index: 564

Text #19

Max Range: 5.5001. Min Range: -5.5001

Max Act: 5.0626. Min Act: -0.1700

Data Index: 95723 (C4 (Web Text))

Max Activating Token Index: 352