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

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

Neuron 1834 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: 3.7524. Min Range: -3.7524

Max Act: 3.7524. Min Act: -0.1700

Data Index: 504009 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 3.7524. Min Range: -3.7524

Max Act: 3.6899. Min Act: -0.1700

Data Index: 1576018 (Python Code)

Max Activating Token Index: 887

Text #2

Max Range: 3.7524. Min Range: -3.7524

Max Act: 3.6899. Min Act: -0.1700

Data Index: 1545798 (Python Code)

Max Activating Token Index: 354

Text #3

Max Range: 3.7524. Min Range: -3.7524

Max Act: 3.7212. Min Act: -0.1700

Data Index: 1480276 (Python Code)

Max Activating Token Index: 631

Text #4

Max Range: 3.7524. Min Range: -3.7524

Max Act: 3.6899. Min Act: -0.1700

Data Index: 781524 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 3.7524. Min Range: -3.7524

Max Act: 3.6899. Min Act: -0.1700

Data Index: 1431232 (Python Code)

Max Activating Token Index: 475

Text #6

Max Range: 3.7524. Min Range: -3.7524

Max Act: 3.5959. Min Act: -0.1700

Data Index: 421872 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 3.7524. Min Range: -3.7524

Max Act: 3.6586. Min Act: -0.1700

Data Index: 1365601 (Python Code)

Max Activating Token Index: 827

Text #8

Max Range: 3.7524. Min Range: -3.7524

Max Act: 3.5959. Min Act: -0.1700

Data Index: 1377300 (Python Code)

Max Activating Token Index: 807

Text #9

Max Range: 3.7524. Min Range: -3.7524

Max Act: 3.5959. Min Act: -0.1700

Data Index: 1630477 (Python Code)

Max Activating Token Index: 947

Text #10

Max Range: 3.7524. Min Range: -3.7524

Max Act: 3.5959. Min Act: -0.1700

Data Index: 1374917 (Python Code)

Max Activating Token Index: 293

Text #11

Max Range: 3.7524. Min Range: -3.7524

Max Act: 3.5646. Min Act: -0.1700

Data Index: 262554 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 3.7524. Min Range: -3.7524

Max Act: 3.5959. Min Act: -0.1700

Data Index: 1443415 (Python Code)

Max Activating Token Index: 730

Text #13

Max Range: 3.7524. Min Range: -3.7524

Max Act: 3.6273. Min Act: -0.1700

Data Index: 1459000 (Python Code)

Max Activating Token Index: 263

Text #14

Max Range: 3.7524. Min Range: -3.7524

Max Act: 3.5959. Min Act: -0.1700

Data Index: 1435412 (Python Code)

Max Activating Token Index: 656

Text #15

Max Range: 3.7524. Min Range: -3.7524

Max Act: 3.5959. Min Act: -0.1700

Data Index: 1508028 (Python Code)

Max Activating Token Index: 152

Text #16

Max Range: 3.7524. Min Range: -3.7524

Max Act: 3.5959. Min Act: -0.1700

Data Index: 1437904 (Python Code)

Max Activating Token Index: 477

Text #17

Max Range: 3.7524. Min Range: -3.7524

Max Act: 3.5333. Min Act: -0.1700

Data Index: 1576888 (Python Code)

Max Activating Token Index: 505

Text #18

Max Range: 3.7524. Min Range: -3.7524

Max Act: 3.5333. Min Act: -0.1700

Data Index: 1432929 (Python Code)

Max Activating Token Index: 438

Text #19

Max Range: 3.7524. Min Range: -3.7524

Max Act: 3.5333. Min Act: -0.1700

Data Index: 1572792 (Python Code)

Max Activating Token Index: 725