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

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

Neuron 88 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: 5.0997. Min Range: -5.0997

Max Act: 5.0997. Min Act: -0.1700

Data Index: 462178 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 5.0997. Min Range: -5.0997

Max Act: 5.0059. Min Act: -0.1700

Data Index: 699559 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 5.0997. Min Range: -5.0997

Max Act: 4.9747. Min Act: -0.1700

Data Index: 627543 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 5.0997. Min Range: -5.0997

Max Act: 4.9434. Min Act: -0.1700

Data Index: 462568 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 5.0997. Min Range: -5.0997

Max Act: 4.8809. Min Act: -0.1700

Data Index: 969321 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 5.0997. Min Range: -5.0997

Max Act: 4.9122. Min Act: -0.1700

Data Index: 1332906 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 5.0997. Min Range: -5.0997

Max Act: 4.9122. Min Act: -0.1700

Data Index: 866074 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 5.0997. Min Range: -5.0997

Max Act: 4.9122. Min Act: -0.1700

Data Index: 858985 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 5.0997. Min Range: -5.0997

Max Act: 4.9122. Min Act: -0.1700

Data Index: 913170 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 5.0997. Min Range: -5.0997

Max Act: 4.8809. Min Act: -0.1700

Data Index: 1349296 (C4 (Web Text))

Max Activating Token Index: 327

Text #10

Max Range: 5.0997. Min Range: -5.0997

Max Act: 4.9122. Min Act: -0.1700

Data Index: 963729 (C4 (Web Text))

Max Activating Token Index: 674

Text #11

Max Range: 5.0997. Min Range: -5.0997

Max Act: 4.8809. Min Act: -0.1700

Data Index: 433903 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 5.0997. Min Range: -5.0997

Max Act: 4.8497. Min Act: -0.1700

Data Index: 566941 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 5.0997. Min Range: -5.0997

Max Act: 4.8497. Min Act: -0.1700

Data Index: 843896 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 5.0997. Min Range: -5.0997

Max Act: 4.8184. Min Act: -0.1700

Data Index: 377322 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 5.0997. Min Range: -5.0997

Max Act: 4.8184. Min Act: -0.1700

Data Index: 510565 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 5.0997. Min Range: -5.0997

Max Act: 4.8184. Min Act: -0.1700

Data Index: 1067625 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 5.0997. Min Range: -5.0997

Max Act: 4.8497. Min Act: -0.1700

Data Index: 767693 (C4 (Web Text))

Max Activating Token Index: 525

Text #18

Max Range: 5.0997. Min Range: -5.0997

Max Act: 4.8497. Min Act: -0.1700

Data Index: 1276739 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 5.0997. Min Range: -5.0997

Max Act: 4.8184. Min Act: -0.1700

Data Index: 914160 (C4 (Web Text))

Max Activating Token Index: 285