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

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

Neuron 1634 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5024. Min Range: -5.5024

Max Act: 5.5024. Min Act: -0.1700

Data Index: 1596009 (Python Code)

Max Activating Token Index: 705

Text #1

Max Range: 5.5024. Min Range: -5.5024

Max Act: 5.5024. Min Act: -0.1700

Data Index: 1514803 (Python Code)

Max Activating Token Index: 608

Text #2

Max Range: 5.5024. Min Range: -5.5024

Max Act: 5.4399. Min Act: -0.1700

Data Index: 1564895 (Python Code)

Max Activating Token Index: 963

Text #3

Max Range: 5.5024. Min Range: -5.5024

Max Act: 5.3774. Min Act: -0.1700

Data Index: 1555388 (Python Code)

Max Activating Token Index: 901

Text #4

Max Range: 5.5024. Min Range: -5.5024

Max Act: 5.4399. Min Act: -0.1700

Data Index: 1431758 (Python Code)

Max Activating Token Index: 721

Text #5

Max Range: 5.5024. Min Range: -5.5024

Max Act: 5.3462. Min Act: -0.1700

Data Index: 1577530 (Python Code)

Max Activating Token Index: 314

Text #6

Max Range: 5.5024. Min Range: -5.5024

Max Act: 5.4087. Min Act: -0.1700

Data Index: 1468316 (Python Code)

Max Activating Token Index: 283

Text #7

Max Range: 5.5024. Min Range: -5.5024

Max Act: 5.4712. Min Act: -0.1700

Data Index: 1532390 (Python Code)

Max Activating Token Index: 667

Text #8

Max Range: 5.5024. Min Range: -5.5024

Max Act: 5.3149. Min Act: -0.1700

Data Index: 1366721 (Python Code)

Max Activating Token Index: 810

Text #9

Max Range: 5.5024. Min Range: -5.5024

Max Act: 5.3462. Min Act: -0.1700

Data Index: 1628081 (Python Code)

Max Activating Token Index: 643

Text #10

Max Range: 5.5024. Min Range: -5.5024

Max Act: 5.3149. Min Act: -0.1700

Data Index: 1429998 (Python Code)

Max Activating Token Index: 741

Text #11

Max Range: 5.5024. Min Range: -5.5024

Max Act: 5.3774. Min Act: -0.1700

Data Index: 1468245 (Python Code)

Max Activating Token Index: 334

Text #12

Max Range: 5.5024. Min Range: -5.5024

Max Act: 5.3462. Min Act: -0.1700

Data Index: 1454669 (Python Code)

Max Activating Token Index: 728

Text #13

Max Range: 5.5024. Min Range: -5.5024

Max Act: 5.3149. Min Act: -0.1700

Data Index: 1637970 (Python Code)

Max Activating Token Index: 334

Text #14

Max Range: 5.5024. Min Range: -5.5024

Max Act: 5.2524. Min Act: -0.1700

Data Index: 1637892 (Python Code)

Max Activating Token Index: 855

Text #15

Max Range: 5.5024. Min Range: -5.5024

Max Act: 5.3462. Min Act: -0.1700

Data Index: 1571046 (Python Code)

Max Activating Token Index: 306

Text #16

Max Range: 5.5024. Min Range: -5.5024

Max Act: 5.3774. Min Act: -0.1700

Data Index: 1374965 (Python Code)

Max Activating Token Index: 894

Text #17

Max Range: 5.5024. Min Range: -5.5024

Max Act: 5.3149. Min Act: -0.1700

Data Index: 1622795 (Python Code)

Max Activating Token Index: 611

Text #18

Max Range: 5.5024. Min Range: -5.5024

Max Act: 5.2837. Min Act: -0.1700

Data Index: 1544264 (Python Code)

Max Activating Token Index: 861

Text #19

Max Range: 5.5024. Min Range: -5.5024

Max Act: 5.3149. Min Act: -0.1700

Data Index: 1362664 (Python Code)

Max Activating Token Index: 702