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

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

Neuron 610 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: 5.7717. Min Range: -5.7717

Max Act: 5.7717. Min Act: -0.1700

Data Index: 1472294 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 5.7717. Min Range: -5.7717

Max Act: 5.3030. Min Act: -0.1700

Data Index: 1607621 (Python Code)

Max Activating Token Index: 782

Text #2

Max Range: 5.7717. Min Range: -5.7717

Max Act: 5.2405. Min Act: -0.1700

Data Index: 1442571 (Python Code)

Max Activating Token Index: 458

Text #3

Max Range: 5.7717. Min Range: -5.7717

Max Act: 5.1155. Min Act: -0.1700

Data Index: 1371027 (Python Code)

Max Activating Token Index: 633

Text #4

Max Range: 5.7717. Min Range: -5.7717

Max Act: 5.1155. Min Act: -0.1700

Data Index: 1584036 (Python Code)

Max Activating Token Index: 454

Text #5

Max Range: 5.7717. Min Range: -5.7717

Max Act: 5.0530. Min Act: -0.1700

Data Index: 1654048 (Python Code)

Max Activating Token Index: 763

Text #6

Max Range: 5.7717. Min Range: -5.7717

Max Act: 5.0217. Min Act: -0.1700

Data Index: 1592963 (Python Code)

Max Activating Token Index: 531

Text #7

Max Range: 5.7717. Min Range: -5.7717

Max Act: 5.0217. Min Act: -0.1700

Data Index: 1378077 (Python Code)

Max Activating Token Index: 654

Text #8

Max Range: 5.7717. Min Range: -5.7717

Max Act: 5.1155. Min Act: -0.1700

Data Index: 1502155 (Python Code)

Max Activating Token Index: 942

Text #9

Max Range: 5.7717. Min Range: -5.7717

Max Act: 5.1155. Min Act: -0.1700

Data Index: 1553837 (Python Code)

Max Activating Token Index: 653

Text #10

Max Range: 5.7717. Min Range: -5.7717

Max Act: 5.0530. Min Act: -0.1700

Data Index: 1608795 (Python Code)

Max Activating Token Index: 681

Text #11

Max Range: 5.7717. Min Range: -5.7717

Max Act: 5.0842. Min Act: -0.1700

Data Index: 1476922 (Python Code)

Max Activating Token Index: 423

Text #12

Max Range: 5.7717. Min Range: -5.7717

Max Act: 4.9905. Min Act: -0.1700

Data Index: 1495159 (Python Code)

Max Activating Token Index: 426

Text #13

Max Range: 5.7717. Min Range: -5.7717

Max Act: 5.1155. Min Act: -0.1700

Data Index: 1376974 (Python Code)

Max Activating Token Index: 578

Text #14

Max Range: 5.7717. Min Range: -5.7717

Max Act: 5.0217. Min Act: -0.1700

Data Index: 1419545 (Python Code)

Max Activating Token Index: 783

Text #15

Max Range: 5.7717. Min Range: -5.7717

Max Act: 5.0217. Min Act: -0.1700

Data Index: 1560440 (Python Code)

Max Activating Token Index: 934

Text #16

Max Range: 5.7717. Min Range: -5.7717

Max Act: 5.0530. Min Act: -0.1700

Data Index: 1436153 (Python Code)

Max Activating Token Index: 154

Text #17

Max Range: 5.7717. Min Range: -5.7717

Max Act: 5.0217. Min Act: -0.1700

Data Index: 1519838 (Python Code)

Max Activating Token Index: 101

Text #18

Max Range: 5.7717. Min Range: -5.7717

Max Act: 5.0530. Min Act: -0.1700

Data Index: 1362810 (Python Code)

Max Activating Token Index: 603

Text #19

Max Range: 5.7717. Min Range: -5.7717

Max Act: 5.0842. Min Act: -0.1700

Data Index: 1449878 (Python Code)

Max Activating Token Index: 910