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

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

Neuron 429 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: 3.3665. Min Range: -3.3665

Max Act: 3.3665. Min Act: -0.1700

Data Index: 1150364 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.3508. Min Act: -0.1700

Data Index: 625949 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.3351. Min Act: -0.1700

Data Index: 1000670 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.3194. Min Act: -0.1700

Data Index: 1519010 (Python Code)

Max Activating Token Index: 2

Text #4

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.3194. Min Act: -0.1700

Data Index: 1442712 (Python Code)

Max Activating Token Index: 2

Text #5

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.3194. Min Act: -0.1700

Data Index: 1492604 (Python Code)

Max Activating Token Index: 2

Text #6

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.3194. Min Act: -0.1700

Data Index: 1522396 (Python Code)

Max Activating Token Index: 2

Text #7

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.3351. Min Act: -0.1700

Data Index: 866386 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.3194. Min Act: -0.1700

Data Index: 1197766 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.3194. Min Act: -0.1700

Data Index: 1312511 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.3194. Min Act: -0.1700

Data Index: 345991 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.3037. Min Act: -0.1700

Data Index: 32851 (C4 (Web Text))

Max Activating Token Index: 1

Text #12

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.3037. Min Act: -0.1700

Data Index: 1466585 (Python Code)

Max Activating Token Index: 1

Text #13

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.3037. Min Act: -0.1700

Data Index: 1407099 (Python Code)

Max Activating Token Index: 1

Text #14

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.3037. Min Act: -0.1700

Data Index: 1593916 (Python Code)

Max Activating Token Index: 5

Text #15

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.3037. Min Act: -0.1700

Data Index: 1586552 (Python Code)

Max Activating Token Index: 1

Text #16

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.3037. Min Act: -0.1700

Data Index: 1531849 (Python Code)

Max Activating Token Index: 1

Text #17

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.3037. Min Act: -0.1700

Data Index: 24336 (C4 (Web Text))

Max Activating Token Index: 1

Text #18

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.3037. Min Act: -0.1700

Data Index: 647 (C4 (Web Text))

Max Activating Token Index: 1

Text #19

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.3037. Min Act: -0.1700

Data Index: 25057 (C4 (Web Text))

Max Activating Token Index: 1