Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1386 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.8621. Min Range: -5.8621

Max Act: 5.8621. Min Act: -0.1700

Data Index: 1181902 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 5.8621. Min Range: -5.8621

Max Act: 5.8308. Min Act: -0.1700

Data Index: 252804 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 5.8621. Min Range: -5.8621

Max Act: 5.7371. Min Act: -0.1700

Data Index: 1041514 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 5.8621. Min Range: -5.8621

Max Act: 5.7058. Min Act: -0.1700

Data Index: 198200 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 5.8621. Min Range: -5.8621

Max Act: 5.6746. Min Act: -0.1700

Data Index: 1129076 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 5.8621. Min Range: -5.8621

Max Act: 5.5496. Min Act: -0.1700

Data Index: 1257267 (C4 (Web Text))

Max Activating Token Index: 784

Text #6

Max Range: 5.8621. Min Range: -5.8621

Max Act: 5.6121. Min Act: -0.1700

Data Index: 376110 (C4 (Web Text))

Max Activating Token Index: 486

Text #7

Max Range: 5.8621. Min Range: -5.8621

Max Act: 5.6433. Min Act: -0.1700

Data Index: 250994 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 5.8621. Min Range: -5.8621

Max Act: 5.6433. Min Act: -0.1700

Data Index: 1100686 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 5.8621. Min Range: -5.8621

Max Act: 5.6433. Min Act: -0.1700

Data Index: 365772 (C4 (Web Text))

Max Activating Token Index: 354

Text #10

Max Range: 5.8621. Min Range: -5.8621

Max Act: 5.6746. Min Act: -0.1700

Data Index: 278772 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 5.8621. Min Range: -5.8621

Max Act: 5.6433. Min Act: -0.1700

Data Index: 93235 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 5.8621. Min Range: -5.8621

Max Act: 5.5183. Min Act: -0.1700

Data Index: 1281880 (C4 (Web Text))

Max Activating Token Index: 884

Text #13

Max Range: 5.8621. Min Range: -5.8621

Max Act: 5.6746. Min Act: -0.1700

Data Index: 322657 (C4 (Web Text))

Max Activating Token Index: 878

Text #14

Max Range: 5.8621. Min Range: -5.8621

Max Act: 5.5496. Min Act: -0.1700

Data Index: 1011392 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 5.8621. Min Range: -5.8621

Max Act: 5.5808. Min Act: -0.1700

Data Index: 938613 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 5.8621. Min Range: -5.8621

Max Act: 5.5808. Min Act: -0.1700

Data Index: 817899 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 5.8621. Min Range: -5.8621

Max Act: 5.5183. Min Act: -0.1700

Data Index: 290759 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 5.8621. Min Range: -5.8621

Max Act: 5.5496. Min Act: -0.1700

Data Index: 50396 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 5.8621. Min Range: -5.8621

Max Act: 5.5496. Min Act: -0.1700

Data Index: 1153787 (C4 (Web Text))

Max Activating Token Index: 470