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

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

Neuron 1647 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: 3.8496. Min Range: -3.8496

Max Act: 3.8496. Min Act: -0.1700

Data Index: 634102 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 3.8496. Min Range: -3.8496

Max Act: 3.7245. Min Act: -0.1700

Data Index: 1162350 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 3.8496. Min Range: -3.8496

Max Act: 3.5523. Min Act: -0.1700

Data Index: 1085716 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 3.8496. Min Range: -3.8496

Max Act: 3.5679. Min Act: -0.1700

Data Index: 641980 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 3.8496. Min Range: -3.8496

Max Act: 3.5209. Min Act: -0.1700

Data Index: 982394 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 3.8496. Min Range: -3.8496

Max Act: 3.5523. Min Act: -0.1700

Data Index: 815239 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 3.8496. Min Range: -3.8496

Max Act: 3.5679. Min Act: -0.1700

Data Index: 1131951 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 3.8496. Min Range: -3.8496

Max Act: 3.5523. Min Act: -0.1700

Data Index: 662417 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 3.8496. Min Range: -3.8496

Max Act: 3.5366. Min Act: -0.1700

Data Index: 913874 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 3.8496. Min Range: -3.8496

Max Act: 3.4896. Min Act: -0.1700

Data Index: 348841 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 3.8496. Min Range: -3.8496

Max Act: 3.4426. Min Act: -0.1700

Data Index: 362566 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 3.8496. Min Range: -3.8496

Max Act: 3.4896. Min Act: -0.1700

Data Index: 798250 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 3.8496. Min Range: -3.8496

Max Act: 3.5053. Min Act: -0.1700

Data Index: 1298978 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 3.8496. Min Range: -3.8496

Max Act: 3.4896. Min Act: -0.1700

Data Index: 616170 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 3.8496. Min Range: -3.8496

Max Act: 3.4896. Min Act: -0.1700

Data Index: 433030 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 3.8496. Min Range: -3.8496

Max Act: 3.4896. Min Act: -0.1700

Data Index: 665664 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 3.8496. Min Range: -3.8496

Max Act: 3.5053. Min Act: -0.1700

Data Index: 476628 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 3.8496. Min Range: -3.8496

Max Act: 3.4112. Min Act: -0.1700

Data Index: 522586 (C4 (Web Text))

Max Activating Token Index: 664

Text #18

Max Range: 3.8496. Min Range: -3.8496

Max Act: 3.4426. Min Act: -0.1700

Data Index: 961120 (C4 (Web Text))

Max Activating Token Index: 302

Text #19

Max Range: 3.8496. Min Range: -3.8496

Max Act: 3.4583. Min Act: -0.1700

Data Index: 584970 (C4 (Web Text))

Max Activating Token Index: 150