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

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

Neuron 450 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: 3.8850. Min Range: -3.8850

Max Act: 3.8850. Min Act: -0.1700

Data Index: 458548 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.7912. Min Act: -0.1700

Data Index: 244951 (C4 (Web Text))

Max Activating Token Index: 689

Text #2

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.8225. Min Act: -0.1700

Data Index: 1006533 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.7912. Min Act: -0.1700

Data Index: 1189467 (C4 (Web Text))

Max Activating Token Index: 486

Text #4

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.6973. Min Act: -0.1700

Data Index: 647455 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.7286. Min Act: -0.1700

Data Index: 245243 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.6660. Min Act: -0.1700

Data Index: 497316 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.6973. Min Act: -0.1700

Data Index: 635686 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.6347. Min Act: -0.1700

Data Index: 166843 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.6660. Min Act: -0.1700

Data Index: 420753 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.6660. Min Act: -0.1700

Data Index: 3757 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.6660. Min Act: -0.1700

Data Index: 1001927 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.6660. Min Act: -0.1700

Data Index: 1229411 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.6347. Min Act: -0.1700

Data Index: 126088 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.6347. Min Act: -0.1700

Data Index: 192969 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.6034. Min Act: -0.1700

Data Index: 432656 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.6034. Min Act: -0.1700

Data Index: 389792 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.6347. Min Act: -0.1700

Data Index: 160514 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.6347. Min Act: -0.1700

Data Index: 353155 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.5721. Min Act: -0.1700

Data Index: 13906 (C4 (Web Text))

Max Activating Token Index: 547