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

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

Neuron 1269 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: 9.3697. Min Range: -9.3697

Max Act: 9.3697. Min Act: -0.1700

Data Index: 1306940 (C4 (Web Text))

Max Activating Token Index: 820

Text #1

Max Range: 9.3697. Min Range: -9.3697

Max Act: 9.0572. Min Act: -0.1699

Data Index: 395508 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 9.3697. Min Range: -9.3697

Max Act: 9.0572. Min Act: -0.1700

Data Index: 21010 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 9.3697. Min Range: -9.3697

Max Act: 9.0572. Min Act: -0.1700

Data Index: 665747 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 9.3697. Min Range: -9.3697

Max Act: 8.8072. Min Act: -0.1700

Data Index: 1277697 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 9.3697. Min Range: -9.3697

Max Act: 8.7447. Min Act: -0.1700

Data Index: 162377 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 9.3697. Min Range: -9.3697

Max Act: 8.7447. Min Act: -0.1700

Data Index: 911832 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 9.3697. Min Range: -9.3697

Max Act: 8.8697. Min Act: -0.1700

Data Index: 644302 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 9.3697. Min Range: -9.3697

Max Act: 8.6822. Min Act: -0.1700

Data Index: 875617 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 9.3697. Min Range: -9.3697

Max Act: 8.7447. Min Act: -0.1699

Data Index: 967200 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 9.3697. Min Range: -9.3697

Max Act: 8.5572. Min Act: -0.1700

Data Index: 520880 (C4 (Web Text))

Max Activating Token Index: 887

Text #11

Max Range: 9.3697. Min Range: -9.3697

Max Act: 8.6197. Min Act: -0.1700

Data Index: 1213514 (C4 (Web Text))

Max Activating Token Index: 726

Text #12

Max Range: 9.3697. Min Range: -9.3697

Max Act: 8.6822. Min Act: -0.1700

Data Index: 814007 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 9.3697. Min Range: -9.3697

Max Act: 8.5572. Min Act: -0.1700

Data Index: 1126380 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 9.3697. Min Range: -9.3697

Max Act: 8.5572. Min Act: -0.1699

Data Index: 257558 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 9.3697. Min Range: -9.3697

Max Act: 8.5572. Min Act: -0.1699

Data Index: 1191063 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 9.3697. Min Range: -9.3697

Max Act: 8.9322. Min Act: -0.1700

Data Index: 1216904 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 9.3697. Min Range: -9.3697

Max Act: 8.4947. Min Act: -0.1699

Data Index: 40079 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 9.3697. Min Range: -9.3697

Max Act: 8.6822. Min Act: -0.1700

Data Index: 1169283 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 9.3697. Min Range: -9.3697

Max Act: 8.4322. Min Act: -0.1700

Data Index: 884877 (C4 (Web Text))

Max Activating Token Index: 443