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

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

Neuron 1059 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: 3.4736. Min Range: -3.4736

Max Act: 3.4736. Min Act: -0.1700

Data Index: 1106621 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 3.4736. Min Range: -3.4736

Max Act: 3.3795. Min Act: -0.1700

Data Index: 1148972 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 3.4736. Min Range: -3.4736

Max Act: 3.3167. Min Act: -0.1700

Data Index: 1651225 (Python Code)

Max Activating Token Index: 130

Text #3

Max Range: 3.4736. Min Range: -3.4736

Max Act: 3.3324. Min Act: -0.1700

Data Index: 1620420 (Python Code)

Max Activating Token Index: 304

Text #4

Max Range: 3.4736. Min Range: -3.4736

Max Act: 3.3010. Min Act: -0.1700

Data Index: 1493644 (Python Code)

Max Activating Token Index: 501

Text #5

Max Range: 3.4736. Min Range: -3.4736

Max Act: 3.3167. Min Act: -0.1700

Data Index: 1484613 (Python Code)

Max Activating Token Index: 61

Text #6

Max Range: 3.4736. Min Range: -3.4736

Max Act: 3.3010. Min Act: -0.1700

Data Index: 1609908 (Python Code)

Max Activating Token Index: 152

Text #7

Max Range: 3.4736. Min Range: -3.4736

Max Act: 3.2853. Min Act: -0.1700

Data Index: 1328983 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 3.4736. Min Range: -3.4736

Max Act: 3.2696. Min Act: -0.1700

Data Index: 1363241 (Python Code)

Max Activating Token Index: 102

Text #9

Max Range: 3.4736. Min Range: -3.4736

Max Act: 3.3010. Min Act: -0.1700

Data Index: 21725 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 3.4736. Min Range: -3.4736

Max Act: 3.2696. Min Act: -0.1700

Data Index: 178870 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 3.4736. Min Range: -3.4736

Max Act: 3.2696. Min Act: -0.1700

Data Index: 1390976 (Python Code)

Max Activating Token Index: 124

Text #12

Max Range: 3.4736. Min Range: -3.4736

Max Act: 3.2381. Min Act: -0.1700

Data Index: 1595188 (Python Code)

Max Activating Token Index: 223

Text #13

Max Range: 3.4736. Min Range: -3.4736

Max Act: 3.2696. Min Act: -0.1700

Data Index: 121177 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 3.4736. Min Range: -3.4736

Max Act: 3.2381. Min Act: -0.1700

Data Index: 1499736 (Python Code)

Max Activating Token Index: 236

Text #15

Max Range: 3.4736. Min Range: -3.4736

Max Act: 3.2224. Min Act: -0.1700

Data Index: 1512488 (Python Code)

Max Activating Token Index: 148

Text #16

Max Range: 3.4736. Min Range: -3.4736

Max Act: 3.2224. Min Act: -0.1700

Data Index: 1431906 (Python Code)

Max Activating Token Index: 121

Text #17

Max Range: 3.4736. Min Range: -3.4736

Max Act: 3.1910. Min Act: -0.1700

Data Index: 1500141 (Python Code)

Max Activating Token Index: 898

Text #18

Max Range: 3.4736. Min Range: -3.4736

Max Act: 3.1910. Min Act: -0.1700

Data Index: 1565481 (Python Code)

Max Activating Token Index: 213

Text #19

Max Range: 3.4736. Min Range: -3.4736

Max Act: 3.2224. Min Act: -0.1700

Data Index: 1576000 (Python Code)

Max Activating Token Index: 82