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

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

Neuron 792 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: 5.4959. Min Range: -5.4959

Max Act: 5.4959. Min Act: -0.1700

Data Index: 31216 (C4 (Web Text))

Max Activating Token Index: 246

Text #1

Max Range: 5.4959. Min Range: -5.4959

Max Act: 5.2459. Min Act: -0.1700

Data Index: 228619 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 5.4959. Min Range: -5.4959

Max Act: 5.2459. Min Act: -0.1700

Data Index: 442722 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 5.4959. Min Range: -5.4959

Max Act: 5.0584. Min Act: -0.1700

Data Index: 362045 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 5.4959. Min Range: -5.4959

Max Act: 5.0584. Min Act: -0.1700

Data Index: 855989 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 5.4959. Min Range: -5.4959

Max Act: 5.1834. Min Act: -0.1700

Data Index: 896852 (C4 (Web Text))

Max Activating Token Index: 481

Text #6

Max Range: 5.4959. Min Range: -5.4959

Max Act: 5.0584. Min Act: -0.1700

Data Index: 778660 (C4 (Web Text))

Max Activating Token Index: 585

Text #7

Max Range: 5.4959. Min Range: -5.4959

Max Act: 5.0584. Min Act: -0.1700

Data Index: 708464 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 5.4959. Min Range: -5.4959

Max Act: 5.0896. Min Act: -0.1700

Data Index: 592134 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 5.4959. Min Range: -5.4959

Max Act: 5.0584. Min Act: -0.1700

Data Index: 996784 (C4 (Web Text))

Max Activating Token Index: 817

Text #10

Max Range: 5.4959. Min Range: -5.4959

Max Act: 5.0584. Min Act: -0.1700

Data Index: 930803 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 5.4959. Min Range: -5.4959

Max Act: 4.9021. Min Act: -0.1700

Data Index: 614261 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 5.4959. Min Range: -5.4959

Max Act: 4.9959. Min Act: -0.1700

Data Index: 8116 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 5.4959. Min Range: -5.4959

Max Act: 5.0271. Min Act: -0.1700

Data Index: 1065388 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 5.4959. Min Range: -5.4959

Max Act: 4.9334. Min Act: -0.1700

Data Index: 682771 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 5.4959. Min Range: -5.4959

Max Act: 4.9646. Min Act: -0.1700

Data Index: 400680 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 5.4959. Min Range: -5.4959

Max Act: 4.9646. Min Act: -0.1700

Data Index: 722831 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 5.4959. Min Range: -5.4959

Max Act: 5.0584. Min Act: -0.1700

Data Index: 96432 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 5.4959. Min Range: -5.4959

Max Act: 4.9646. Min Act: -0.1700

Data Index: 633163 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 5.4959. Min Range: -5.4959

Max Act: 4.9959. Min Act: -0.1700

Data Index: 225732 (C4 (Web Text))

Max Activating Token Index: 318