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

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

Neuron 1044 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: 5.7082. Min Range: -5.7082

Max Act: 5.7082. Min Act: -0.1700

Data Index: 152891 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 5.7082. Min Range: -5.7082

Max Act: 5.5832. Min Act: -0.1700

Data Index: 1283752 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 5.7082. Min Range: -5.7082

Max Act: 5.6145. Min Act: -0.1700

Data Index: 635299 (C4 (Web Text))

Max Activating Token Index: 626

Text #3

Max Range: 5.7082. Min Range: -5.7082

Max Act: 5.5520. Min Act: -0.1700

Data Index: 56585 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 5.7082. Min Range: -5.7082

Max Act: 5.5520. Min Act: -0.1700

Data Index: 1240732 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 5.7082. Min Range: -5.7082

Max Act: 5.5520. Min Act: -0.1700

Data Index: 290132 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 5.7082. Min Range: -5.7082

Max Act: 5.5520. Min Act: -0.1700

Data Index: 1096554 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 5.7082. Min Range: -5.7082

Max Act: 5.5207. Min Act: -0.1700

Data Index: 796569 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 5.7082. Min Range: -5.7082

Max Act: 5.4895. Min Act: -0.1700

Data Index: 457277 (C4 (Web Text))

Max Activating Token Index: 196

Text #9

Max Range: 5.7082. Min Range: -5.7082

Max Act: 5.4895. Min Act: -0.1700

Data Index: 137369 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 5.7082. Min Range: -5.7082

Max Act: 5.4582. Min Act: -0.1700

Data Index: 153105 (C4 (Web Text))

Max Activating Token Index: 693

Text #11

Max Range: 5.7082. Min Range: -5.7082

Max Act: 5.4270. Min Act: -0.1700

Data Index: 347328 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 5.7082. Min Range: -5.7082

Max Act: 5.4270. Min Act: -0.1700

Data Index: 1279408 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 5.7082. Min Range: -5.7082

Max Act: 5.4895. Min Act: -0.1700

Data Index: 656931 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 5.7082. Min Range: -5.7082

Max Act: 5.4270. Min Act: -0.1700

Data Index: 653163 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 5.7082. Min Range: -5.7082

Max Act: 5.3957. Min Act: -0.1700

Data Index: 274547 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 5.7082. Min Range: -5.7082

Max Act: 5.3957. Min Act: -0.1700

Data Index: 226149 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 5.7082. Min Range: -5.7082

Max Act: 5.4582. Min Act: -0.1700

Data Index: 449560 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 5.7082. Min Range: -5.7082

Max Act: 5.4895. Min Act: -0.1700

Data Index: 793863 (C4 (Web Text))

Max Activating Token Index: 284

Text #19

Max Range: 5.7082. Min Range: -5.7082

Max Act: 5.4270. Min Act: -0.1700

Data Index: 289553 (C4 (Web Text))

Max Activating Token Index: 358