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

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

Neuron 962 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.1376. Min Range: -3.1376

Max Act: 3.1061. Min Act: -0.1700

Data Index: 220216 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 3.1376. Min Range: -3.1376

Max Act: 3.1376. Min Act: -0.1700

Data Index: 694508 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 3.1376. Min Range: -3.1376

Max Act: 3.0588. Min Act: -0.1700

Data Index: 350053 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 3.1376. Min Range: -3.1376

Max Act: 3.0745. Min Act: -0.1700

Data Index: 809308 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 3.1376. Min Range: -3.1376

Max Act: 3.0903. Min Act: -0.1700

Data Index: 596296 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 3.1376. Min Range: -3.1376

Max Act: 3.0430. Min Act: -0.1700

Data Index: 1171310 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 3.1376. Min Range: -3.1376

Max Act: 3.0430. Min Act: -0.1700

Data Index: 862114 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 3.1376. Min Range: -3.1376

Max Act: 3.0430. Min Act: -0.1700

Data Index: 440221 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 3.1376. Min Range: -3.1376

Max Act: 3.0430. Min Act: -0.1700

Data Index: 311042 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 3.1376. Min Range: -3.1376

Max Act: 3.0430. Min Act: -0.1700

Data Index: 355296 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 3.1376. Min Range: -3.1376

Max Act: 2.9956. Min Act: -0.1700

Data Index: 30477 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 3.1376. Min Range: -3.1376

Max Act: 3.0272. Min Act: -0.1700

Data Index: 637385 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 3.1376. Min Range: -3.1376

Max Act: 3.0430. Min Act: -0.1700

Data Index: 1357373 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 3.1376. Min Range: -3.1376

Max Act: 3.0272. Min Act: -0.1700

Data Index: 534463 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 3.1376. Min Range: -3.1376

Max Act: 3.0114. Min Act: -0.1700

Data Index: 938877 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 3.1376. Min Range: -3.1376

Max Act: 3.0272. Min Act: -0.1700

Data Index: 931375 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 3.1376. Min Range: -3.1376

Max Act: 3.0114. Min Act: -0.1700

Data Index: 31596 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 3.1376. Min Range: -3.1376

Max Act: 3.0114. Min Act: -0.1700

Data Index: 1074588 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 3.1376. Min Range: -3.1376

Max Act: 2.9956. Min Act: -0.1700

Data Index: 825321 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 3.1376. Min Range: -3.1376

Max Act: 3.0114. Min Act: -0.1700

Data Index: 175876 (C4 (Web Text))

Max Activating Token Index: 428