Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1759 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.8481. Min Act: -0.1700

Data Index: 395108 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.7855. Min Act: -0.1700

Data Index: 1039941 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.7230. Min Act: -0.1700

Data Index: 1177221 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.7230. Min Act: -0.1700

Data Index: 1016429 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.6604. Min Act: -0.1700

Data Index: 627520 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.6917. Min Act: -0.1700

Data Index: 409459 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.6604. Min Act: -0.1700

Data Index: 1221571 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.6917. Min Act: -0.1700

Data Index: 819695 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.6291. Min Act: -0.1700

Data Index: 680730 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.6291. Min Act: -0.1700

Data Index: 647041 (C4 (Web Text))

Max Activating Token Index: 683

Text #10

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.6291. Min Act: -0.1700

Data Index: 667654 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.6291. Min Act: -0.1700

Data Index: 614677 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.5664. Min Act: -0.1700

Data Index: 342330 (C4 (Web Text))

Max Activating Token Index: 376

Text #13

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.6291. Min Act: -0.1700

Data Index: 722756 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.6291. Min Act: -0.1700

Data Index: 236365 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.5664. Min Act: -0.1700

Data Index: 468962 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.6291. Min Act: -0.1700

Data Index: 256629 (C4 (Web Text))

Max Activating Token Index: 439

Text #17

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.5978. Min Act: -0.1700

Data Index: 194591 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.5978. Min Act: -0.1700

Data Index: 828313 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.5978. Min Act: -0.1700

Data Index: 185432 (C4 (Web Text))

Max Activating Token Index: 152