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

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

Neuron 1364 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.1614. Min Range: -3.1614

Max Act: 3.1614. Min Act: -0.1700

Data Index: 863249 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 3.1614. Min Range: -3.1614

Max Act: 3.0511. Min Act: -0.1700

Data Index: 1533368 (Python Code)

Max Activating Token Index: 896

Text #2

Max Range: 3.1614. Min Range: -3.1614

Max Act: 3.0195. Min Act: -0.1700

Data Index: 1478514 (Python Code)

Max Activating Token Index: 896

Text #3

Max Range: 3.1614. Min Range: -3.1614

Max Act: 3.0195. Min Act: -0.1700

Data Index: 1590620 (Python Code)

Max Activating Token Index: 969

Text #4

Max Range: 3.1614. Min Range: -3.1614

Max Act: 3.0037. Min Act: -0.1700

Data Index: 1540636 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 3.1614. Min Range: -3.1614

Max Act: 3.0037. Min Act: -0.1700

Data Index: 1364761 (Python Code)

Max Activating Token Index: 824

Text #6

Max Range: 3.1614. Min Range: -3.1614

Max Act: 3.0195. Min Act: -0.1700

Data Index: 1502710 (Python Code)

Max Activating Token Index: 663

Text #7

Max Range: 3.1614. Min Range: -3.1614

Max Act: 2.9879. Min Act: -0.1700

Data Index: 1553679 (Python Code)

Max Activating Token Index: 899

Text #8

Max Range: 3.1614. Min Range: -3.1614

Max Act: 3.0195. Min Act: -0.1700

Data Index: 1418002 (Python Code)

Max Activating Token Index: 705

Text #9

Max Range: 3.1614. Min Range: -3.1614

Max Act: 2.9879. Min Act: -0.1700

Data Index: 1127952 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 3.1614. Min Range: -3.1614

Max Act: 2.9721. Min Act: -0.1700

Data Index: 1464355 (Python Code)

Max Activating Token Index: 884

Text #11

Max Range: 3.1614. Min Range: -3.1614

Max Act: 2.9879. Min Act: -0.1700

Data Index: 1437755 (Python Code)

Max Activating Token Index: 1005

Text #12

Max Range: 3.1614. Min Range: -3.1614

Max Act: 2.9879. Min Act: -0.1700

Data Index: 1528244 (Python Code)

Max Activating Token Index: 870

Text #13

Max Range: 3.1614. Min Range: -3.1614

Max Act: 2.9721. Min Act: -0.1700

Data Index: 1543658 (Python Code)

Max Activating Token Index: 609

Text #14

Max Range: 3.1614. Min Range: -3.1614

Max Act: 2.9879. Min Act: -0.1700

Data Index: 1575151 (Python Code)

Max Activating Token Index: 276

Text #15

Max Range: 3.1614. Min Range: -3.1614

Max Act: 2.9879. Min Act: -0.1700

Data Index: 1485867 (Python Code)

Max Activating Token Index: 658

Text #16

Max Range: 3.1614. Min Range: -3.1614

Max Act: 2.9721. Min Act: -0.1700

Data Index: 1652332 (Python Code)

Max Activating Token Index: 282

Text #17

Max Range: 3.1614. Min Range: -3.1614

Max Act: 3.0037. Min Act: -0.1700

Data Index: 1513572 (Python Code)

Max Activating Token Index: 700

Text #18

Max Range: 3.1614. Min Range: -3.1614

Max Act: 2.9562. Min Act: -0.1700

Data Index: 1437899 (Python Code)

Max Activating Token Index: 788

Text #19

Max Range: 3.1614. Min Range: -3.1614

Max Act: 2.9721. Min Act: -0.1700

Data Index: 1592673 (Python Code)

Max Activating Token Index: 658