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

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

Neuron 584 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: 5.4546. Min Range: -5.4546

Max Act: 5.4546. Min Act: -0.1700

Data Index: 930968 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 5.4546. Min Range: -5.4546

Max Act: 5.3921. Min Act: -0.1700

Data Index: 766103 (C4 (Web Text))

Max Activating Token Index: 844

Text #2

Max Range: 5.4546. Min Range: -5.4546

Max Act: 5.2983. Min Act: -0.1700

Data Index: 185985 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 5.4546. Min Range: -5.4546

Max Act: 5.2983. Min Act: -0.1700

Data Index: 798940 (C4 (Web Text))

Max Activating Token Index: 737

Text #4

Max Range: 5.4546. Min Range: -5.4546

Max Act: 5.1421. Min Act: -0.1700

Data Index: 1192808 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 5.4546. Min Range: -5.4546

Max Act: 5.1108. Min Act: -0.1700

Data Index: 741450 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 5.4546. Min Range: -5.4546

Max Act: 5.1733. Min Act: -0.1700

Data Index: 1211011 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 5.4546. Min Range: -5.4546

Max Act: 5.1421. Min Act: -0.1700

Data Index: 756783 (C4 (Web Text))

Max Activating Token Index: 676

Text #8

Max Range: 5.4546. Min Range: -5.4546

Max Act: 5.1108. Min Act: -0.1700

Data Index: 569864 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 5.4546. Min Range: -5.4546

Max Act: 5.1733. Min Act: -0.1700

Data Index: 472544 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 5.4546. Min Range: -5.4546

Max Act: 5.0483. Min Act: -0.1700

Data Index: 427673 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 5.4546. Min Range: -5.4546

Max Act: 5.1421. Min Act: -0.1700

Data Index: 88265 (C4 (Web Text))

Max Activating Token Index: 682

Text #12

Max Range: 5.4546. Min Range: -5.4546

Max Act: 4.9546. Min Act: -0.1700

Data Index: 57285 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 5.4546. Min Range: -5.4546

Max Act: 5.0796. Min Act: -0.1700

Data Index: 50260 (C4 (Web Text))

Max Activating Token Index: 609

Text #14

Max Range: 5.4546. Min Range: -5.4546

Max Act: 4.9858. Min Act: -0.1700

Data Index: 322675 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 5.4546. Min Range: -5.4546

Max Act: 4.9546. Min Act: -0.1700

Data Index: 68372 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 5.4546. Min Range: -5.4546

Max Act: 5.0171. Min Act: -0.1700

Data Index: 9199 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 5.4546. Min Range: -5.4546

Max Act: 4.9546. Min Act: -0.1700

Data Index: 223897 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 5.4546. Min Range: -5.4546

Max Act: 4.9546. Min Act: -0.1700

Data Index: 560003 (C4 (Web Text))

Max Activating Token Index: 333

Text #19

Max Range: 5.4546. Min Range: -5.4546

Max Act: 4.9233. Min Act: -0.1700

Data Index: 150465 (C4 (Web Text))

Max Activating Token Index: 299