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

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

Neuron 409 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: 3.7948. Min Range: -3.7948

Max Act: 3.7948. Min Act: -0.1700

Data Index: 854965 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 3.7948. Min Range: -3.7948

Max Act: 3.7010. Min Act: -0.1700

Data Index: 176523 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 3.7948. Min Range: -3.7948

Max Act: 3.6697. Min Act: -0.1700

Data Index: 799543 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 3.7948. Min Range: -3.7948

Max Act: 3.6697. Min Act: -0.1700

Data Index: 871428 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 3.7948. Min Range: -3.7948

Max Act: 3.7010. Min Act: -0.1700

Data Index: 728609 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 3.7948. Min Range: -3.7948

Max Act: 3.6697. Min Act: -0.1700

Data Index: 1083924 (C4 (Web Text))

Max Activating Token Index: 238

Text #6

Max Range: 3.7948. Min Range: -3.7948

Max Act: 3.6697. Min Act: -0.1700

Data Index: 1176479 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 3.7948. Min Range: -3.7948

Max Act: 3.6071. Min Act: -0.1700

Data Index: 233256 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 3.7948. Min Range: -3.7948

Max Act: 3.6071. Min Act: -0.1700

Data Index: 1146453 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 3.7948. Min Range: -3.7948

Max Act: 3.6071. Min Act: -0.1700

Data Index: 222865 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 3.7948. Min Range: -3.7948

Max Act: 3.6384. Min Act: -0.1700

Data Index: 981535 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 3.7948. Min Range: -3.7948

Max Act: 3.6384. Min Act: -0.1700

Data Index: 575533 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 3.7948. Min Range: -3.7948

Max Act: 3.6384. Min Act: -0.1700

Data Index: 10858 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 3.7948. Min Range: -3.7948

Max Act: 3.6384. Min Act: -0.1700

Data Index: 1003446 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 3.7948. Min Range: -3.7948

Max Act: 3.6384. Min Act: -0.1700

Data Index: 394460 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 3.7948. Min Range: -3.7948

Max Act: 3.6384. Min Act: -0.1700

Data Index: 872699 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 3.7948. Min Range: -3.7948

Max Act: 3.6384. Min Act: -0.1700

Data Index: 630210 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 3.7948. Min Range: -3.7948

Max Act: 3.6384. Min Act: -0.1700

Data Index: 625642 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 3.7948. Min Range: -3.7948

Max Act: 3.5757. Min Act: -0.1700

Data Index: 1012706 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 3.7948. Min Range: -3.7948

Max Act: 3.5757. Min Act: -0.1700

Data Index: 506333 (C4 (Web Text))

Max Activating Token Index: 332