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

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

Neuron 1722 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: 13.2098. Min Range: -13.2098

Max Act: 13.2098. Min Act: -0.1700

Data Index: 379527 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 13.2098. Min Range: -13.2098

Max Act: 12.8348. Min Act: -0.1700

Data Index: 1462760 (Python Code)

Max Activating Token Index: 952

Text #2

Max Range: 13.2098. Min Range: -13.2098

Max Act: 12.9598. Min Act: -0.1700

Data Index: 1146059 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 13.2098. Min Range: -13.2098

Max Act: 12.6473. Min Act: -0.1700

Data Index: 89179 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 13.2098. Min Range: -13.2098

Max Act: 12.6473. Min Act: -0.1700

Data Index: 514871 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 13.2098. Min Range: -13.2098

Max Act: 12.5223. Min Act: -0.1700

Data Index: 1230452 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 13.2098. Min Range: -13.2098

Max Act: 12.5223. Min Act: -0.1700

Data Index: 1039738 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 13.2098. Min Range: -13.2098

Max Act: 12.5223. Min Act: -0.1700

Data Index: 986325 (C4 (Web Text))

Max Activating Token Index: 876

Text #8

Max Range: 13.2098. Min Range: -13.2098

Max Act: 12.1473. Min Act: -0.1700

Data Index: 757040 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 13.2098. Min Range: -13.2098

Max Act: 12.3973. Min Act: -0.1700

Data Index: 215906 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 13.2098. Min Range: -13.2098

Max Act: 12.2098. Min Act: -0.1700

Data Index: 667706 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 13.2098. Min Range: -13.2098

Max Act: 12.2723. Min Act: -0.1700

Data Index: 810391 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 13.2098. Min Range: -13.2098

Max Act: 12.1473. Min Act: -0.1700

Data Index: 1102767 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 13.2098. Min Range: -13.2098

Max Act: 12.2098. Min Act: -0.1700

Data Index: 535442 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 13.2098. Min Range: -13.2098

Max Act: 12.1473. Min Act: -0.1700

Data Index: 1559062 (Python Code)

Max Activating Token Index: 769

Text #15

Max Range: 13.2098. Min Range: -13.2098

Max Act: 11.9598. Min Act: -0.1700

Data Index: 1489323 (Python Code)

Max Activating Token Index: 440

Text #16

Max Range: 13.2098. Min Range: -13.2098

Max Act: 12.2098. Min Act: -0.1700

Data Index: 274843 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 13.2098. Min Range: -13.2098

Max Act: 11.8973. Min Act: -0.1700

Data Index: 444282 (C4 (Web Text))

Max Activating Token Index: 856

Text #18

Max Range: 13.2098. Min Range: -13.2098

Max Act: 11.8973. Min Act: -0.1700

Data Index: 144970 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 13.2098. Min Range: -13.2098

Max Act: 11.7723. Min Act: -0.1700

Data Index: 834093 (C4 (Web Text))

Max Activating Token Index: 331