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

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

Neuron 1041 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1564. Min Range: -3.1564

Max Act: 3.1564. Min Act: -0.1700

Data Index: 1258428 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 3.1564. Min Range: -3.1564

Max Act: 3.1564. Min Act: -0.1700

Data Index: 752099 (C4 (Web Text))

Max Activating Token Index: 682

Text #2

Max Range: 3.1564. Min Range: -3.1564

Max Act: 3.1249. Min Act: -0.1700

Data Index: 48525 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 3.1564. Min Range: -3.1564

Max Act: 3.1249. Min Act: -0.1700

Data Index: 199348 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 3.1564. Min Range: -3.1564

Max Act: 3.1091. Min Act: -0.1700

Data Index: 1139566 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 3.1564. Min Range: -3.1564

Max Act: 3.0934. Min Act: -0.1700

Data Index: 679165 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 3.1564. Min Range: -3.1564

Max Act: 3.0934. Min Act: -0.1700

Data Index: 679756 (C4 (Web Text))

Max Activating Token Index: 102

Text #7

Max Range: 3.1564. Min Range: -3.1564

Max Act: 3.0776. Min Act: -0.1700

Data Index: 697360 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 3.1564. Min Range: -3.1564

Max Act: 3.1091. Min Act: -0.1700

Data Index: 347409 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 3.1564. Min Range: -3.1564

Max Act: 3.0776. Min Act: -0.1700

Data Index: 833596 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 3.1564. Min Range: -3.1564

Max Act: 3.0776. Min Act: -0.1700

Data Index: 289662 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 3.1564. Min Range: -3.1564

Max Act: 3.0776. Min Act: -0.1700

Data Index: 829105 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 3.1564. Min Range: -3.1564

Max Act: 3.0776. Min Act: -0.1700

Data Index: 487268 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 3.1564. Min Range: -3.1564

Max Act: 3.0460. Min Act: -0.1700

Data Index: 204659 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 3.1564. Min Range: -3.1564

Max Act: 3.0302. Min Act: -0.1700

Data Index: 1017607 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 3.1564. Min Range: -3.1564

Max Act: 3.0618. Min Act: -0.1700

Data Index: 1198048 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 3.1564. Min Range: -3.1564

Max Act: 3.0460. Min Act: -0.1700

Data Index: 709853 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 3.1564. Min Range: -3.1564

Max Act: 3.0460. Min Act: -0.1700

Data Index: 282192 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 3.1564. Min Range: -3.1564

Max Act: 3.0460. Min Act: -0.1700

Data Index: 20266 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 3.1564. Min Range: -3.1564

Max Act: 3.0302. Min Act: -0.1700

Data Index: 1061147 (C4 (Web Text))

Max Activating Token Index: 6