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

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

Neuron 589 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: 3.6824. Min Range: -3.6824

Max Act: 3.6824. Min Act: -0.1700

Data Index: 1614343 (Python Code)

Max Activating Token Index: 60

Text #1

Max Range: 3.6824. Min Range: -3.6824

Max Act: 3.6511. Min Act: -0.1700

Data Index: 1540528 (Python Code)

Max Activating Token Index: 71

Text #2

Max Range: 3.6824. Min Range: -3.6824

Max Act: 3.6355. Min Act: -0.1700

Data Index: 1428232 (Python Code)

Max Activating Token Index: 68

Text #3

Max Range: 3.6824. Min Range: -3.6824

Max Act: 3.5885. Min Act: -0.1700

Data Index: 1556243 (Python Code)

Max Activating Token Index: 141

Text #4

Max Range: 3.6824. Min Range: -3.6824

Max Act: 3.5729. Min Act: -0.1700

Data Index: 1394614 (Python Code)

Max Activating Token Index: 17

Text #5

Max Range: 3.6824. Min Range: -3.6824

Max Act: 3.5729. Min Act: -0.1700

Data Index: 1498426 (Python Code)

Max Activating Token Index: 207

Text #6

Max Range: 3.6824. Min Range: -3.6824

Max Act: 3.5885. Min Act: -0.1700

Data Index: 1597361 (Python Code)

Max Activating Token Index: 17

Text #7

Max Range: 3.6824. Min Range: -3.6824

Max Act: 3.5572. Min Act: -0.1700

Data Index: 1593591 (Python Code)

Max Activating Token Index: 106

Text #8

Max Range: 3.6824. Min Range: -3.6824

Max Act: 3.5885. Min Act: -0.1700

Data Index: 1549372 (Python Code)

Max Activating Token Index: 164

Text #9

Max Range: 3.6824. Min Range: -3.6824

Max Act: 3.5729. Min Act: -0.1700

Data Index: 1482668 (Python Code)

Max Activating Token Index: 96

Text #10

Max Range: 3.6824. Min Range: -3.6824

Max Act: 3.5415. Min Act: -0.1700

Data Index: 1580425 (Python Code)

Max Activating Token Index: 124

Text #11

Max Range: 3.6824. Min Range: -3.6824

Max Act: 3.5729. Min Act: -0.1700

Data Index: 1462583 (Python Code)

Max Activating Token Index: 164

Text #12

Max Range: 3.6824. Min Range: -3.6824

Max Act: 3.5259. Min Act: -0.1700

Data Index: 1554006 (Python Code)

Max Activating Token Index: 67

Text #13

Max Range: 3.6824. Min Range: -3.6824

Max Act: 3.5572. Min Act: -0.1700

Data Index: 1425067 (Python Code)

Max Activating Token Index: 274

Text #14

Max Range: 3.6824. Min Range: -3.6824

Max Act: 3.5415. Min Act: -0.1700

Data Index: 1552604 (Python Code)

Max Activating Token Index: 54

Text #15

Max Range: 3.6824. Min Range: -3.6824

Max Act: 3.5102. Min Act: -0.1700

Data Index: 1391629 (Python Code)

Max Activating Token Index: 220

Text #16

Max Range: 3.6824. Min Range: -3.6824

Max Act: 3.5259. Min Act: -0.1700

Data Index: 1576057 (Python Code)

Max Activating Token Index: 215

Text #17

Max Range: 3.6824. Min Range: -3.6824

Max Act: 3.5572. Min Act: -0.1700

Data Index: 1593821 (Python Code)

Max Activating Token Index: 146

Text #18

Max Range: 3.6824. Min Range: -3.6824

Max Act: 3.5259. Min Act: -0.1700

Data Index: 1515258 (Python Code)

Max Activating Token Index: 15

Text #19

Max Range: 3.6824. Min Range: -3.6824

Max Act: 3.5102. Min Act: -0.1700

Data Index: 1380985 (Python Code)

Max Activating Token Index: 72