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

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

Neuron 1090 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: 3.9494. Min Range: -3.9494

Max Act: 3.9494. Min Act: -0.1700

Data Index: 1001930 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 3.9494. Min Range: -3.9494

Max Act: 3.8556. Min Act: -0.1700

Data Index: 521601 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 3.9494. Min Range: -3.9494

Max Act: 3.8243. Min Act: -0.1700

Data Index: 197396 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 3.9494. Min Range: -3.9494

Max Act: 3.8556. Min Act: -0.1700

Data Index: 831874 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 3.9494. Min Range: -3.9494

Max Act: 3.8556. Min Act: -0.1700

Data Index: 953574 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 3.9494. Min Range: -3.9494

Max Act: 3.7930. Min Act: -0.1700

Data Index: 123193 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 3.9494. Min Range: -3.9494

Max Act: 3.8556. Min Act: -0.1700

Data Index: 12242 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 3.9494. Min Range: -3.9494

Max Act: 3.7930. Min Act: -0.1700

Data Index: 101108 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 3.9494. Min Range: -3.9494

Max Act: 3.7618. Min Act: -0.1700

Data Index: 236920 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 3.9494. Min Range: -3.9494

Max Act: 3.7618. Min Act: -0.1700

Data Index: 136438 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 3.9494. Min Range: -3.9494

Max Act: 3.7305. Min Act: -0.1700

Data Index: 648808 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 3.9494. Min Range: -3.9494

Max Act: 3.7618. Min Act: -0.1700

Data Index: 6089 (C4 (Web Text))

Max Activating Token Index: 617

Text #12

Max Range: 3.9494. Min Range: -3.9494

Max Act: 3.6992. Min Act: -0.1700

Data Index: 138475 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 3.9494. Min Range: -3.9494

Max Act: 3.7618. Min Act: -0.1700

Data Index: 202487 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 3.9494. Min Range: -3.9494

Max Act: 3.6992. Min Act: -0.1700

Data Index: 1108490 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 3.9494. Min Range: -3.9494

Max Act: 3.6679. Min Act: -0.1700

Data Index: 275672 (C4 (Web Text))

Max Activating Token Index: 339

Text #16

Max Range: 3.9494. Min Range: -3.9494

Max Act: 3.6679. Min Act: -0.1700

Data Index: 196789 (C4 (Web Text))

Max Activating Token Index: 360

Text #17

Max Range: 3.9494. Min Range: -3.9494

Max Act: 3.6679. Min Act: -0.1700

Data Index: 266646 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 3.9494. Min Range: -3.9494

Max Act: 3.6992. Min Act: -0.1700

Data Index: 212246 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 3.9494. Min Range: -3.9494

Max Act: 3.6366. Min Act: -0.1700

Data Index: 567264 (C4 (Web Text))

Max Activating Token Index: 747