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

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

Neuron 1469 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: 7.0486. Min Range: -7.0486

Max Act: 7.0486. Min Act: -0.1700

Data Index: 952635 (C4 (Web Text))

Max Activating Token Index: 805

Text #1

Max Range: 7.0486. Min Range: -7.0486

Max Act: 7.0174. Min Act: -0.1700

Data Index: 522239 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 7.0486. Min Range: -7.0486

Max Act: 6.9549. Min Act: -0.1700

Data Index: 350269 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 7.0486. Min Range: -7.0486

Max Act: 6.9861. Min Act: -0.1700

Data Index: 804703 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 7.0486. Min Range: -7.0486

Max Act: 6.9236. Min Act: -0.1700

Data Index: 533433 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 7.0486. Min Range: -7.0486

Max Act: 6.9236. Min Act: -0.1700

Data Index: 341505 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 7.0486. Min Range: -7.0486

Max Act: 6.8924. Min Act: -0.1700

Data Index: 458846 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 7.0486. Min Range: -7.0486

Max Act: 6.9236. Min Act: -0.1700

Data Index: 560176 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 7.0486. Min Range: -7.0486

Max Act: 6.8924. Min Act: -0.1700

Data Index: 1071560 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 7.0486. Min Range: -7.0486

Max Act: 6.8924. Min Act: -0.1700

Data Index: 797533 (C4 (Web Text))

Max Activating Token Index: 645

Text #10

Max Range: 7.0486. Min Range: -7.0486

Max Act: 6.8924. Min Act: -0.1700

Data Index: 384675 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 7.0486. Min Range: -7.0486

Max Act: 6.8611. Min Act: -0.1700

Data Index: 21523 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 7.0486. Min Range: -7.0486

Max Act: 6.7986. Min Act: -0.1700

Data Index: 948851 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 7.0486. Min Range: -7.0486

Max Act: 6.8299. Min Act: -0.1700

Data Index: 266778 (C4 (Web Text))

Max Activating Token Index: 643

Text #14

Max Range: 7.0486. Min Range: -7.0486

Max Act: 6.8611. Min Act: -0.1700

Data Index: 211265 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 7.0486. Min Range: -7.0486

Max Act: 6.7986. Min Act: -0.1700

Data Index: 1328362 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 7.0486. Min Range: -7.0486

Max Act: 6.7986. Min Act: -0.1700

Data Index: 791628 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 7.0486. Min Range: -7.0486

Max Act: 6.7986. Min Act: -0.1700

Data Index: 489427 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 7.0486. Min Range: -7.0486

Max Act: 6.7674. Min Act: -0.1700

Data Index: 574286 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 7.0486. Min Range: -7.0486

Max Act: 6.7986. Min Act: -0.1700

Data Index: 28775 (C4 (Web Text))

Max Activating Token Index: 200