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

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

Neuron 1412 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4962. Min Range: -5.4962

Max Act: 5.4962. Min Act: -0.1700

Data Index: 1600126 (Python Code)

Max Activating Token Index: 300

Text #1

Max Range: 5.4962. Min Range: -5.4962

Max Act: 5.4337. Min Act: -0.1700

Data Index: 1428081 (Python Code)

Max Activating Token Index: 130

Text #2

Max Range: 5.4962. Min Range: -5.4962

Max Act: 5.4962. Min Act: -0.1700

Data Index: 1602528 (Python Code)

Max Activating Token Index: 43

Text #3

Max Range: 5.4962. Min Range: -5.4962

Max Act: 5.4024. Min Act: -0.1700

Data Index: 1603662 (Python Code)

Max Activating Token Index: 386

Text #4

Max Range: 5.4962. Min Range: -5.4962

Max Act: 5.4024. Min Act: -0.1700

Data Index: 1648693 (Python Code)

Max Activating Token Index: 787

Text #5

Max Range: 5.4962. Min Range: -5.4962

Max Act: 5.3712. Min Act: -0.1700

Data Index: 1628081 (Python Code)

Max Activating Token Index: 666

Text #6

Max Range: 5.4962. Min Range: -5.4962

Max Act: 5.3712. Min Act: -0.1700

Data Index: 1496038 (Python Code)

Max Activating Token Index: 782

Text #7

Max Range: 5.4962. Min Range: -5.4962

Max Act: 5.3712. Min Act: -0.1700

Data Index: 1472384 (Python Code)

Max Activating Token Index: 126

Text #8

Max Range: 5.4962. Min Range: -5.4962

Max Act: 5.3087. Min Act: -0.1700

Data Index: 1558603 (Python Code)

Max Activating Token Index: 896

Text #9

Max Range: 5.4962. Min Range: -5.4962

Max Act: 5.4024. Min Act: -0.1700

Data Index: 1605993 (Python Code)

Max Activating Token Index: 744

Text #10

Max Range: 5.4962. Min Range: -5.4962

Max Act: 5.3399. Min Act: -0.1700

Data Index: 1514803 (Python Code)

Max Activating Token Index: 629

Text #11

Max Range: 5.4962. Min Range: -5.4962

Max Act: 5.4024. Min Act: -0.1700

Data Index: 1622795 (Python Code)

Max Activating Token Index: 632

Text #12

Max Range: 5.4962. Min Range: -5.4962

Max Act: 5.3712. Min Act: -0.1700

Data Index: 1470995 (Python Code)

Max Activating Token Index: 106

Text #13

Max Range: 5.4962. Min Range: -5.4962

Max Act: 5.3712. Min Act: -0.1700

Data Index: 1362759 (Python Code)

Max Activating Token Index: 114

Text #14

Max Range: 5.4962. Min Range: -5.4962

Max Act: 5.3399. Min Act: -0.1700

Data Index: 1625591 (Python Code)

Max Activating Token Index: 610

Text #15

Max Range: 5.4962. Min Range: -5.4962

Max Act: 5.3087. Min Act: -0.1700

Data Index: 1621327 (Python Code)

Max Activating Token Index: 839

Text #16

Max Range: 5.4962. Min Range: -5.4962

Max Act: 5.3087. Min Act: -0.1700

Data Index: 1389855 (Python Code)

Max Activating Token Index: 789

Text #17

Max Range: 5.4962. Min Range: -5.4962

Max Act: 5.3087. Min Act: -0.1700

Data Index: 1637892 (Python Code)

Max Activating Token Index: 875

Text #18

Max Range: 5.4962. Min Range: -5.4962

Max Act: 5.3087. Min Act: -0.1700

Data Index: 1474225 (Python Code)

Max Activating Token Index: 735

Text #19

Max Range: 5.4962. Min Range: -5.4962

Max Act: 5.3399. Min Act: -0.1700

Data Index: 1555388 (Python Code)

Max Activating Token Index: 918