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

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

Neuron 2003 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: 3.3722. Min Range: -3.3722

Max Act: 3.3722. Min Act: -0.1700

Data Index: 626351 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.3252. Min Act: -0.1700

Data Index: 930572 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.3252. Min Act: -0.1700

Data Index: 794443 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2780. Min Act: -0.1700

Data Index: 715701 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2780. Min Act: -0.1700

Data Index: 73943 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2780. Min Act: -0.1700

Data Index: 972767 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2466. Min Act: -0.1700

Data Index: 249534 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2309. Min Act: -0.1700

Data Index: 209186 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2152. Min Act: -0.1700

Data Index: 627963 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2152. Min Act: -0.1700

Data Index: 757117 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.1994. Min Act: -0.1700

Data Index: 448238 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2466. Min Act: -0.1700

Data Index: 1075752 (C4 (Web Text))

Max Activating Token Index: 519

Text #12

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2309. Min Act: -0.1700

Data Index: 1093723 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2152. Min Act: -0.1700

Data Index: 1116818 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2309. Min Act: -0.1700

Data Index: 1140367 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2309. Min Act: -0.1700

Data Index: 713332 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2309. Min Act: -0.1700

Data Index: 515419 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.1994. Min Act: -0.1700

Data Index: 148884 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.1994. Min Act: -0.1700

Data Index: 496571 (C4 (Web Text))

Max Activating Token Index: 447

Text #19

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.1994. Min Act: -0.1700

Data Index: 238920 (C4 (Web Text))

Max Activating Token Index: 744