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

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

Neuron 1938 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: 7.2416. Min Range: -7.2416

Max Act: 7.2416. Min Act: -0.1700

Data Index: 291405 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 7.2416. Min Range: -7.2416

Max Act: 7.2416. Min Act: -0.1700

Data Index: 438059 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 7.2416. Min Range: -7.2416

Max Act: 7.1791. Min Act: -0.1700

Data Index: 591483 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 7.2416. Min Range: -7.2416

Max Act: 7.1479. Min Act: -0.1700

Data Index: 721780 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 7.2416. Min Range: -7.2416

Max Act: 7.1479. Min Act: -0.1700

Data Index: 935100 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 7.2416. Min Range: -7.2416

Max Act: 7.1166. Min Act: -0.1700

Data Index: 108595 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 7.2416. Min Range: -7.2416

Max Act: 7.1791. Min Act: -0.1700

Data Index: 426793 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 7.2416. Min Range: -7.2416

Max Act: 7.1479. Min Act: -0.1700

Data Index: 69152 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 7.2416. Min Range: -7.2416

Max Act: 7.0854. Min Act: -0.1700

Data Index: 1356002 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 7.2416. Min Range: -7.2416

Max Act: 7.0541. Min Act: -0.1700

Data Index: 811139 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 7.2416. Min Range: -7.2416

Max Act: 7.0541. Min Act: -0.1700

Data Index: 348092 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 7.2416. Min Range: -7.2416

Max Act: 7.0541. Min Act: -0.1700

Data Index: 635803 (C4 (Web Text))

Max Activating Token Index: 519

Text #12

Max Range: 7.2416. Min Range: -7.2416

Max Act: 7.0229. Min Act: -0.1700

Data Index: 948384 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 7.2416. Min Range: -7.2416

Max Act: 6.9604. Min Act: -0.1700

Data Index: 402170 (C4 (Web Text))

Max Activating Token Index: 449

Text #14

Max Range: 7.2416. Min Range: -7.2416

Max Act: 7.0541. Min Act: -0.1700

Data Index: 329057 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 7.2416. Min Range: -7.2416

Max Act: 6.9916. Min Act: -0.1700

Data Index: 409756 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 7.2416. Min Range: -7.2416

Max Act: 7.0854. Min Act: -0.1700

Data Index: 858685 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 7.2416. Min Range: -7.2416

Max Act: 6.9291. Min Act: -0.1700

Data Index: 1177974 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 7.2416. Min Range: -7.2416

Max Act: 6.9291. Min Act: -0.1700

Data Index: 1333038 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 7.2416. Min Range: -7.2416

Max Act: 6.9604. Min Act: -0.1700

Data Index: 446892 (C4 (Web Text))

Max Activating Token Index: 853