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

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

Neuron 1607 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: 3.2168. Min Range: -3.2168

Max Act: 3.2168. Min Act: -0.1700

Data Index: 1517419 (Python Code)

Max Activating Token Index: 172

Text #1

Max Range: 3.2168. Min Range: -3.2168

Max Act: 3.2168. Min Act: -0.1700

Data Index: 1376162 (Python Code)

Max Activating Token Index: 336

Text #2

Max Range: 3.2168. Min Range: -3.2168

Max Act: 3.1539. Min Act: -0.1700

Data Index: 1419223 (Python Code)

Max Activating Token Index: 286

Text #3

Max Range: 3.2168. Min Range: -3.2168

Max Act: 3.1381. Min Act: -0.1700

Data Index: 612633 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 3.2168. Min Range: -3.2168

Max Act: 3.1381. Min Act: -0.1700

Data Index: 1577742 (Python Code)

Max Activating Token Index: 111

Text #5

Max Range: 3.2168. Min Range: -3.2168

Max Act: 3.1381. Min Act: -0.1700

Data Index: 1383981 (Python Code)

Max Activating Token Index: 172

Text #6

Max Range: 3.2168. Min Range: -3.2168

Max Act: 3.1381. Min Act: -0.1700

Data Index: 1380604 (Python Code)

Max Activating Token Index: 226

Text #7

Max Range: 3.2168. Min Range: -3.2168

Max Act: 3.1224. Min Act: -0.1700

Data Index: 1590760 (Python Code)

Max Activating Token Index: 85

Text #8

Max Range: 3.2168. Min Range: -3.2168

Max Act: 3.1224. Min Act: -0.1700

Data Index: 1453572 (Python Code)

Max Activating Token Index: 140

Text #9

Max Range: 3.2168. Min Range: -3.2168

Max Act: 3.1066. Min Act: -0.1700

Data Index: 663216 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 3.2168. Min Range: -3.2168

Max Act: 3.0909. Min Act: -0.1700

Data Index: 1563505 (Python Code)

Max Activating Token Index: 100

Text #11

Max Range: 3.2168. Min Range: -3.2168

Max Act: 3.1066. Min Act: -0.1700

Data Index: 1434267 (Python Code)

Max Activating Token Index: 164

Text #12

Max Range: 3.2168. Min Range: -3.2168

Max Act: 3.1224. Min Act: -0.1700

Data Index: 1549025 (Python Code)

Max Activating Token Index: 46

Text #13

Max Range: 3.2168. Min Range: -3.2168

Max Act: 3.0751. Min Act: -0.1700

Data Index: 1400817 (Python Code)

Max Activating Token Index: 308

Text #14

Max Range: 3.2168. Min Range: -3.2168

Max Act: 3.1066. Min Act: -0.1700

Data Index: 1384188 (Python Code)

Max Activating Token Index: 103

Text #15

Max Range: 3.2168. Min Range: -3.2168

Max Act: 3.0909. Min Act: -0.1700

Data Index: 1390781 (Python Code)

Max Activating Token Index: 198

Text #16

Max Range: 3.2168. Min Range: -3.2168

Max Act: 3.0909. Min Act: -0.1700

Data Index: 374930 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 3.2168. Min Range: -3.2168

Max Act: 3.0751. Min Act: -0.1700

Data Index: 1441628 (Python Code)

Max Activating Token Index: 375

Text #18

Max Range: 3.2168. Min Range: -3.2168

Max Act: 3.0593. Min Act: -0.1700

Data Index: 1379322 (Python Code)

Max Activating Token Index: 479

Text #19

Max Range: 3.2168. Min Range: -3.2168

Max Act: 3.0751. Min Act: -0.1700

Data Index: 1528863 (Python Code)

Max Activating Token Index: 210