Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1266 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.7903. Min Act: -0.1700

Data Index: 194020 (C4 (Web Text))

Max Activating Token Index: 821

Text #1

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.7434. Min Act: -0.1700

Data Index: 891816 (C4 (Web Text))

Max Activating Token Index: 309

Text #2

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.6025. Min Act: -0.1700

Data Index: 1374868 (Python Code)

Max Activating Token Index: 696

Text #3

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.5242. Min Act: -0.1700

Data Index: 1272431 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.5242. Min Act: -0.1700

Data Index: 1105484 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.5242. Min Act: -0.1700

Data Index: 769404 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.4929. Min Act: -0.1700

Data Index: 1601975 (Python Code)

Max Activating Token Index: 663

Text #7

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.5086. Min Act: -0.1700

Data Index: 765183 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.4929. Min Act: -0.1700

Data Index: 470345 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.4929. Min Act: -0.1700

Data Index: 563353 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.5086. Min Act: -0.1700

Data Index: 795902 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.4772. Min Act: -0.1700

Data Index: 674397 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.4615. Min Act: -0.1700

Data Index: 865058 (C4 (Web Text))

Max Activating Token Index: 253

Text #13

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.4615. Min Act: -0.1700

Data Index: 1346253 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.4772. Min Act: -0.1700

Data Index: 1526597 (Python Code)

Max Activating Token Index: 782

Text #15

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.4772. Min Act: -0.1700

Data Index: 1653636 (Python Code)

Max Activating Token Index: 847

Text #16

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.4459. Min Act: -0.1700

Data Index: 1325546 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.4615. Min Act: -0.1700

Data Index: 1162348 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.4615. Min Act: -0.1700

Data Index: 613453 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.4459. Min Act: -0.1700

Data Index: 489106 (C4 (Web Text))

Max Activating Token Index: 507