Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1313 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.1427. Min Range: -3.1427

Max Act: 3.1427. Min Act: -0.1700

Data Index: 620827 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 3.1427. Min Range: -3.1427

Max Act: 3.0646. Min Act: -0.1700

Data Index: 425663 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 3.1427. Min Range: -3.1427

Max Act: 3.0536. Min Act: -0.1700

Data Index: 1192167 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 3.1427. Min Range: -3.1427

Max Act: 3.0573. Min Act: -0.1700

Data Index: 52482 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 3.1427. Min Range: -3.1427

Max Act: 3.0183. Min Act: -0.1700

Data Index: 1281458 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 3.1427. Min Range: -3.1427

Max Act: 2.9903. Min Act: -0.1700

Data Index: 439926 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 3.1427. Min Range: -3.1427

Max Act: 3.0006. Min Act: -0.1700

Data Index: 975998 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 3.1427. Min Range: -3.1427

Max Act: 2.9637. Min Act: -0.1700

Data Index: 103840 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 3.1427. Min Range: -3.1427

Max Act: 2.9519. Min Act: -0.1698

Data Index: 1106344 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 3.1427. Min Range: -3.1427

Max Act: 2.9609. Min Act: -0.1700

Data Index: 1162925 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 3.1427. Min Range: -3.1427

Max Act: 2.9497. Min Act: -0.1700

Data Index: 100660 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 3.1427. Min Range: -3.1427

Max Act: 2.9233. Min Act: -0.1700

Data Index: 872545 (C4 (Web Text))

Max Activating Token Index: 761

Text #12

Max Range: 3.1427. Min Range: -3.1427

Max Act: 2.9314. Min Act: -0.1700

Data Index: 116327 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 3.1427. Min Range: -3.1427

Max Act: 2.9088. Min Act: -0.1700

Data Index: 1627144 (Python Code)

Max Activating Token Index: 770

Text #14

Max Range: 3.1427. Min Range: -3.1427

Max Act: 2.9077. Min Act: -0.1700

Data Index: 1051583 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 3.1427. Min Range: -3.1427

Max Act: 2.9060. Min Act: -0.1700

Data Index: 689351 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 3.1427. Min Range: -3.1427

Max Act: 2.9096. Min Act: -0.1700

Data Index: 790181 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 3.1427. Min Range: -3.1427

Max Act: 2.9102. Min Act: -0.1700

Data Index: 1355688 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 3.1427. Min Range: -3.1427

Max Act: 2.8886. Min Act: -0.1700

Data Index: 993404 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 3.1427. Min Range: -3.1427

Max Act: 2.9021. Min Act: -0.1700

Data Index: 940725 (C4 (Web Text))

Max Activating Token Index: 244