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

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

Neuron 47 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.7139. Min Act: -0.1700

Data Index: 737193 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.7452. Min Act: -0.1700

Data Index: 317463 (C4 (Web Text))

Max Activating Token Index: 287

Text #2

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.6513. Min Act: -0.1700

Data Index: 108980 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.6200. Min Act: -0.1700

Data Index: 1216706 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.6200. Min Act: -0.1700

Data Index: 1098777 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.5887. Min Act: -0.1700

Data Index: 817232 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.5574. Min Act: -0.1700

Data Index: 795506 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.5261. Min Act: -0.1700

Data Index: 1139909 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.5574. Min Act: -0.1700

Data Index: 665569 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.5574. Min Act: -0.1700

Data Index: 773873 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.6200. Min Act: -0.1700

Data Index: 368061 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.6513. Min Act: -0.1700

Data Index: 408270 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.4634. Min Act: -0.1700

Data Index: 1055036 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.5261. Min Act: -0.1700

Data Index: 408484 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.7139. Min Act: -0.1700

Data Index: 838848 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.5574. Min Act: -0.1700

Data Index: 560657 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.5261. Min Act: -0.1700

Data Index: 567580 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.6200. Min Act: -0.1700

Data Index: 181546 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.5261. Min Act: -0.1700

Data Index: 1045267 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.5261. Min Act: -0.1700

Data Index: 643667 (C4 (Web Text))

Max Activating Token Index: 785