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

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

Neuron 376 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: 5.3928. Min Range: -5.3928

Max Act: 5.3928. Min Act: -0.1700

Data Index: 964551 (C4 (Web Text))

Max Activating Token Index: 569

Text #1

Max Range: 5.3928. Min Range: -5.3928

Max Act: 5.1741. Min Act: -0.1700

Data Index: 674770 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 5.3928. Min Range: -5.3928

Max Act: 5.1116. Min Act: -0.1700

Data Index: 413408 (C4 (Web Text))

Max Activating Token Index: 702

Text #3

Max Range: 5.3928. Min Range: -5.3928

Max Act: 5.0803. Min Act: -0.1700

Data Index: 525721 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 5.3928. Min Range: -5.3928

Max Act: 5.0178. Min Act: -0.1700

Data Index: 1149829 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 5.3928. Min Range: -5.3928

Max Act: 5.0803. Min Act: -0.1700

Data Index: 710150 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 5.3928. Min Range: -5.3928

Max Act: 4.9866. Min Act: -0.1700

Data Index: 997541 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 5.3928. Min Range: -5.3928

Max Act: 4.9241. Min Act: -0.1700

Data Index: 700581 (C4 (Web Text))

Max Activating Token Index: 549

Text #8

Max Range: 5.3928. Min Range: -5.3928

Max Act: 4.9241. Min Act: -0.1700

Data Index: 332939 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 5.3928. Min Range: -5.3928

Max Act: 4.8928. Min Act: -0.1700

Data Index: 634046 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 5.3928. Min Range: -5.3928

Max Act: 4.9241. Min Act: -0.1700

Data Index: 823000 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 5.3928. Min Range: -5.3928

Max Act: 4.9241. Min Act: -0.1700

Data Index: 300666 (C4 (Web Text))

Max Activating Token Index: 514

Text #12

Max Range: 5.3928. Min Range: -5.3928

Max Act: 4.9241. Min Act: -0.1700

Data Index: 587906 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 5.3928. Min Range: -5.3928

Max Act: 4.8616. Min Act: -0.1700

Data Index: 647549 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 5.3928. Min Range: -5.3928

Max Act: 4.8303. Min Act: -0.1700

Data Index: 169838 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 5.3928. Min Range: -5.3928

Max Act: 4.8303. Min Act: -0.1700

Data Index: 407156 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 5.3928. Min Range: -5.3928

Max Act: 4.7991. Min Act: -0.1700

Data Index: 203105 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 5.3928. Min Range: -5.3928

Max Act: 4.7991. Min Act: -0.1700

Data Index: 207662 (C4 (Web Text))

Max Activating Token Index: 267

Text #18

Max Range: 5.3928. Min Range: -5.3928

Max Act: 4.7678. Min Act: -0.1700

Data Index: 1066444 (C4 (Web Text))

Max Activating Token Index: 992

Text #19

Max Range: 5.3928. Min Range: -5.3928

Max Act: 4.7366. Min Act: -0.1700

Data Index: 1042060 (C4 (Web Text))

Max Activating Token Index: 969