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

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

Neuron 1853 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.7969. Min Act: -0.1700

Data Index: 1337142 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.7969. Min Act: -0.1700

Data Index: 1134953 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.7344. Min Act: -0.1700

Data Index: 762621 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.7500. Min Act: -0.1700

Data Index: 1006698 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.7813. Min Act: -0.1700

Data Index: 416740 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.6874. Min Act: -0.1700

Data Index: 290460 (C4 (Web Text))

Max Activating Token Index: 444

Text #6

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.7187. Min Act: -0.1700

Data Index: 357808 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.6874. Min Act: -0.1700

Data Index: 751571 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.7031. Min Act: -0.1700

Data Index: 537541 (C4 (Web Text))

Max Activating Token Index: 582

Text #9

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.7031. Min Act: -0.1700

Data Index: 1187258 (C4 (Web Text))

Max Activating Token Index: 400

Text #10

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.7031. Min Act: -0.1700

Data Index: 67903 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.7031. Min Act: -0.1700

Data Index: 745637 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.6874. Min Act: -0.1700

Data Index: 548866 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.6874. Min Act: -0.1700

Data Index: 1353642 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.6874. Min Act: -0.1700

Data Index: 371004 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.6874. Min Act: -0.1700

Data Index: 523888 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.6718. Min Act: -0.1700

Data Index: 1350718 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.6718. Min Act: -0.1700

Data Index: 990744 (C4 (Web Text))

Max Activating Token Index: 714

Text #18

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.6561. Min Act: -0.1700

Data Index: 1090615 (C4 (Web Text))

Max Activating Token Index: 891

Text #19

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.6874. Min Act: -0.1700

Data Index: 41247 (C4 (Web Text))

Max Activating Token Index: 671