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

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

Neuron 1659 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: 5.9479. Min Range: -5.9479

Max Act: 5.9479. Min Act: -0.1700

Data Index: 133838 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 5.9479. Min Range: -5.9479

Max Act: 5.8854. Min Act: -0.1700

Data Index: 556854 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 5.9479. Min Range: -5.9479

Max Act: 5.7917. Min Act: -0.1699

Data Index: 465018 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 5.9479. Min Range: -5.9479

Max Act: 5.7917. Min Act: -0.1700

Data Index: 386703 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 5.9479. Min Range: -5.9479

Max Act: 5.7604. Min Act: -0.1700

Data Index: 87852 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 5.9479. Min Range: -5.9479

Max Act: 5.7292. Min Act: -0.1700

Data Index: 1242300 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 5.9479. Min Range: -5.9479

Max Act: 5.6979. Min Act: -0.1700

Data Index: 279768 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 5.9479. Min Range: -5.9479

Max Act: 5.6979. Min Act: -0.1700

Data Index: 227170 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 5.9479. Min Range: -5.9479

Max Act: 5.6667. Min Act: -0.1700

Data Index: 903753 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 5.9479. Min Range: -5.9479

Max Act: 5.6354. Min Act: -0.1700

Data Index: 279628 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 5.9479. Min Range: -5.9479

Max Act: 5.6354. Min Act: -0.1700

Data Index: 775656 (C4 (Web Text))

Max Activating Token Index: 1008

Text #11

Max Range: 5.9479. Min Range: -5.9479

Max Act: 5.6667. Min Act: -0.1696

Data Index: 25668 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 5.9479. Min Range: -5.9479

Max Act: 5.6042. Min Act: -0.1700

Data Index: 991147 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 5.9479. Min Range: -5.9479

Max Act: 5.6042. Min Act: -0.1700

Data Index: 776684 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 5.9479. Min Range: -5.9479

Max Act: 5.5104. Min Act: -0.1699

Data Index: 1104236 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 5.9479. Min Range: -5.9479

Max Act: 5.5417. Min Act: -0.1700

Data Index: 841962 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 5.9479. Min Range: -5.9479

Max Act: 5.5104. Min Act: -0.1700

Data Index: 248864 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 5.9479. Min Range: -5.9479

Max Act: 5.5729. Min Act: -0.1700

Data Index: 756790 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 5.9479. Min Range: -5.9479

Max Act: 5.6042. Min Act: -0.1700

Data Index: 850108 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 5.9479. Min Range: -5.9479

Max Act: 5.5417. Min Act: -0.1700

Data Index: 690305 (C4 (Web Text))

Max Activating Token Index: 794