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

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

Neuron 307 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2282. Min Range: -3.2282

Max Act: 3.2282. Min Act: -0.1700

Data Index: 821653 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 3.2282. Min Range: -3.2282

Max Act: 3.1968. Min Act: -0.1700

Data Index: 1516831 (Python Code)

Max Activating Token Index: 168

Text #2

Max Range: 3.2282. Min Range: -3.2282

Max Act: 3.1968. Min Act: -0.1700

Data Index: 629292 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 3.2282. Min Range: -3.2282

Max Act: 3.1968. Min Act: -0.1700

Data Index: 1384889 (Python Code)

Max Activating Token Index: 445

Text #4

Max Range: 3.2282. Min Range: -3.2282

Max Act: 3.1653. Min Act: -0.1700

Data Index: 1648080 (Python Code)

Max Activating Token Index: 970

Text #5

Max Range: 3.2282. Min Range: -3.2282

Max Act: 3.1810. Min Act: -0.1700

Data Index: 1347625 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 3.2282. Min Range: -3.2282

Max Act: 3.1338. Min Act: -0.1700

Data Index: 1526555 (Python Code)

Max Activating Token Index: 455

Text #7

Max Range: 3.2282. Min Range: -3.2282

Max Act: 3.1338. Min Act: -0.1700

Data Index: 1015783 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 3.2282. Min Range: -3.2282

Max Act: 3.1023. Min Act: -0.1700

Data Index: 1396993 (Python Code)

Max Activating Token Index: 742

Text #9

Max Range: 3.2282. Min Range: -3.2282

Max Act: 3.1180. Min Act: -0.1700

Data Index: 1424771 (Python Code)

Max Activating Token Index: 884

Text #10

Max Range: 3.2282. Min Range: -3.2282

Max Act: 3.1180. Min Act: -0.1700

Data Index: 1590674 (Python Code)

Max Activating Token Index: 829

Text #11

Max Range: 3.2282. Min Range: -3.2282

Max Act: 3.0865. Min Act: -0.1700

Data Index: 1395237 (Python Code)

Max Activating Token Index: 549

Text #12

Max Range: 3.2282. Min Range: -3.2282

Max Act: 3.0707. Min Act: -0.1700

Data Index: 301881 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 3.2282. Min Range: -3.2282

Max Act: 3.0865. Min Act: -0.1700

Data Index: 1404195 (Python Code)

Max Activating Token Index: 779

Text #14

Max Range: 3.2282. Min Range: -3.2282

Max Act: 3.0707. Min Act: -0.1700

Data Index: 1571224 (Python Code)

Max Activating Token Index: 33

Text #15

Max Range: 3.2282. Min Range: -3.2282

Max Act: 3.0707. Min Act: -0.1700

Data Index: 1617398 (Python Code)

Max Activating Token Index: 350

Text #16

Max Range: 3.2282. Min Range: -3.2282

Max Act: 3.0707. Min Act: -0.1700

Data Index: 1631791 (Python Code)

Max Activating Token Index: 490

Text #17

Max Range: 3.2282. Min Range: -3.2282

Max Act: 3.0391. Min Act: -0.1700

Data Index: 1509340 (Python Code)

Max Activating Token Index: 6

Text #18

Max Range: 3.2282. Min Range: -3.2282

Max Act: 3.0549. Min Act: -0.1700

Data Index: 1521398 (Python Code)

Max Activating Token Index: 36

Text #19

Max Range: 3.2282. Min Range: -3.2282

Max Act: 3.0549. Min Act: -0.1700

Data Index: 1388417 (Python Code)

Max Activating Token Index: 841