Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1266 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.9662. Min Range: -3.9662

Max Act: 3.9662. Min Act: -0.1700

Data Index: 1511745 (Python Code)

Max Activating Token Index: 376

Text #1

Max Range: 3.9662. Min Range: -3.9662

Max Act: 3.6846. Min Act: -0.1700

Data Index: 1519497 (Python Code)

Max Activating Token Index: 223

Text #2

Max Range: 3.9662. Min Range: -3.9662

Max Act: 3.5907. Min Act: -0.1700

Data Index: 1422728 (Python Code)

Max Activating Token Index: 209

Text #3

Max Range: 3.9662. Min Range: -3.9662

Max Act: 3.4497. Min Act: -0.1700

Data Index: 1441717 (Python Code)

Max Activating Token Index: 62

Text #4

Max Range: 3.9662. Min Range: -3.9662

Max Act: 3.4497. Min Act: -0.1700

Data Index: 1404373 (Python Code)

Max Activating Token Index: 155

Text #5

Max Range: 3.9662. Min Range: -3.9662

Max Act: 3.4967. Min Act: -0.1700

Data Index: 1507343 (Python Code)

Max Activating Token Index: 139

Text #6

Max Range: 3.9662. Min Range: -3.9662

Max Act: 3.4340. Min Act: -0.1700

Data Index: 1497527 (Python Code)

Max Activating Token Index: 176

Text #7

Max Range: 3.9662. Min Range: -3.9662

Max Act: 3.3870. Min Act: -0.1700

Data Index: 1456867 (Python Code)

Max Activating Token Index: 69

Text #8

Max Range: 3.9662. Min Range: -3.9662

Max Act: 3.3713. Min Act: -0.1700

Data Index: 1448207 (Python Code)

Max Activating Token Index: 33

Text #9

Max Range: 3.9662. Min Range: -3.9662

Max Act: 3.2928. Min Act: -0.1700

Data Index: 1475252 (Python Code)

Max Activating Token Index: 126

Text #10

Max Range: 3.9662. Min Range: -3.9662

Max Act: 3.3713. Min Act: -0.1700

Data Index: 1616328 (Python Code)

Max Activating Token Index: 151

Text #11

Max Range: 3.9662. Min Range: -3.9662

Max Act: 3.2614. Min Act: -0.1700

Data Index: 1577072 (Python Code)

Max Activating Token Index: 215

Text #12

Max Range: 3.9662. Min Range: -3.9662

Max Act: 3.2614. Min Act: -0.1700

Data Index: 1448614 (Python Code)

Max Activating Token Index: 111

Text #13

Max Range: 3.9662. Min Range: -3.9662

Max Act: 3.2614. Min Act: -0.1700

Data Index: 1446254 (Python Code)

Max Activating Token Index: 222

Text #14

Max Range: 3.9662. Min Range: -3.9662

Max Act: 3.2614. Min Act: -0.1700

Data Index: 1465717 (Python Code)

Max Activating Token Index: 111

Text #15

Max Range: 3.9662. Min Range: -3.9662

Max Act: 3.2142. Min Act: -0.1700

Data Index: 1465993 (Python Code)

Max Activating Token Index: 257

Text #16

Max Range: 3.9662. Min Range: -3.9662

Max Act: 3.2142. Min Act: -0.1700

Data Index: 1569739 (Python Code)

Max Activating Token Index: 204

Text #17

Max Range: 3.9662. Min Range: -3.9662

Max Act: 3.1670. Min Act: -0.1700

Data Index: 1591395 (Python Code)

Max Activating Token Index: 77

Text #18

Max Range: 3.9662. Min Range: -3.9662

Max Act: 3.2142. Min Act: -0.1700

Data Index: 1627970 (Python Code)

Max Activating Token Index: 83

Text #19

Max Range: 3.9662. Min Range: -3.9662

Max Act: 3.2142. Min Act: -0.1700

Data Index: 1639102 (Python Code)

Max Activating Token Index: 69