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

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

Neuron 1275 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: 3.8216. Min Range: -3.8216

Max Act: 3.8216. Min Act: -0.1700

Data Index: 415013 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.8216. Min Act: -0.1700

Data Index: 552310 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.8216. Min Act: -0.1700

Data Index: 868521 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.7903. Min Act: -0.1700

Data Index: 815015 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.7590. Min Act: -0.1700

Data Index: 629972 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.7590. Min Act: -0.1700

Data Index: 1225914 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.6964. Min Act: -0.1700

Data Index: 82223 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.6964. Min Act: -0.1700

Data Index: 345382 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.6651. Min Act: -0.1700

Data Index: 110253 (C4 (Web Text))

Max Activating Token Index: 445

Text #9

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.6338. Min Act: -0.1700

Data Index: 484799 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.6338. Min Act: -0.1700

Data Index: 548863 (C4 (Web Text))

Max Activating Token Index: 529

Text #11

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.6338. Min Act: -0.1700

Data Index: 34762 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.6025. Min Act: -0.1700

Data Index: 307662 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.5712. Min Act: -0.1700

Data Index: 773382 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.6025. Min Act: -0.1700

Data Index: 559006 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.6025. Min Act: -0.1700

Data Index: 447399 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.5712. Min Act: -0.1700

Data Index: 741029 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.5712. Min Act: -0.1700

Data Index: 765379 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.5712. Min Act: -0.1700

Data Index: 28710 (C4 (Web Text))

Max Activating Token Index: 1020

Text #19

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.5712. Min Act: -0.1700

Data Index: 494664 (C4 (Web Text))

Max Activating Token Index: 236