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

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

Neuron 1379 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1701. Min Range: -5.1701

Max Act: 5.1701. Min Act: -0.1700

Data Index: 1090578 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 5.1701. Min Range: -5.1701

Max Act: 5.1389. Min Act: -0.1700

Data Index: 869280 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 5.1701. Min Range: -5.1701

Max Act: 5.0764. Min Act: -0.1700

Data Index: 48118 (C4 (Web Text))

Max Activating Token Index: 329

Text #3

Max Range: 5.1701. Min Range: -5.1701

Max Act: 5.0451. Min Act: -0.1700

Data Index: 151562 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 5.1701. Min Range: -5.1701

Max Act: 4.9826. Min Act: -0.1700

Data Index: 1108893 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 5.1701. Min Range: -5.1701

Max Act: 5.0451. Min Act: -0.1700

Data Index: 841846 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 5.1701. Min Range: -5.1701

Max Act: 4.9826. Min Act: -0.1700

Data Index: 1269307 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 5.1701. Min Range: -5.1701

Max Act: 5.0764. Min Act: -0.1700

Data Index: 359879 (C4 (Web Text))

Max Activating Token Index: 584

Text #8

Max Range: 5.1701. Min Range: -5.1701

Max Act: 5.0139. Min Act: -0.1700

Data Index: 742582 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 5.1701. Min Range: -5.1701

Max Act: 5.0139. Min Act: -0.1700

Data Index: 378814 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 5.1701. Min Range: -5.1701

Max Act: 4.9826. Min Act: -0.1700

Data Index: 1109404 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 5.1701. Min Range: -5.1701

Max Act: 5.0139. Min Act: -0.1700

Data Index: 704140 (C4 (Web Text))

Max Activating Token Index: 583

Text #12

Max Range: 5.1701. Min Range: -5.1701

Max Act: 4.9826. Min Act: -0.1700

Data Index: 638704 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 5.1701. Min Range: -5.1701

Max Act: 4.9826. Min Act: -0.1700

Data Index: 532311 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 5.1701. Min Range: -5.1701

Max Act: 4.9826. Min Act: -0.1700

Data Index: 213668 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 5.1701. Min Range: -5.1701

Max Act: 4.9826. Min Act: -0.1700

Data Index: 259023 (C4 (Web Text))

Max Activating Token Index: 466

Text #16

Max Range: 5.1701. Min Range: -5.1701

Max Act: 5.0139. Min Act: -0.1700

Data Index: 81820 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 5.1701. Min Range: -5.1701

Max Act: 4.9826. Min Act: -0.1700

Data Index: 457147 (C4 (Web Text))

Max Activating Token Index: 478

Text #18

Max Range: 5.1701. Min Range: -5.1701

Max Act: 4.9826. Min Act: -0.1700

Data Index: 114987 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 5.1701. Min Range: -5.1701

Max Act: 4.9514. Min Act: -0.1700

Data Index: 273665 (C4 (Web Text))

Max Activating Token Index: 466