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

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

Neuron 456 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: 3.1665. Min Range: -3.1665

Max Act: 3.1665. Min Act: -0.1700

Data Index: 451667 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 3.1665. Min Range: -3.1665

Max Act: 3.1507. Min Act: -0.1700

Data Index: 436045 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 3.1665. Min Range: -3.1665

Max Act: 3.1507. Min Act: -0.1700

Data Index: 239662 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 3.1665. Min Range: -3.1665

Max Act: 3.1350. Min Act: -0.1700

Data Index: 943366 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 3.1665. Min Range: -3.1665

Max Act: 3.0719. Min Act: -0.1700

Data Index: 94848 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 3.1665. Min Range: -3.1665

Max Act: 3.0877. Min Act: -0.1700

Data Index: 382592 (C4 (Web Text))

Max Activating Token Index: 674

Text #6

Max Range: 3.1665. Min Range: -3.1665

Max Act: 3.0877. Min Act: -0.1700

Data Index: 1044367 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 3.1665. Min Range: -3.1665

Max Act: 3.0877. Min Act: -0.1700

Data Index: 720 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 3.1665. Min Range: -3.1665

Max Act: 3.0719. Min Act: -0.1700

Data Index: 1325264 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 3.1665. Min Range: -3.1665

Max Act: 3.0719. Min Act: -0.1700

Data Index: 1249127 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 3.1665. Min Range: -3.1665

Max Act: 3.0877. Min Act: -0.1700

Data Index: 351438 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 3.1665. Min Range: -3.1665

Max Act: 3.0719. Min Act: -0.1700

Data Index: 504826 (C4 (Web Text))

Max Activating Token Index: 3

Text #12

Max Range: 3.1665. Min Range: -3.1665

Max Act: 3.0403. Min Act: -0.1700

Data Index: 728402 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 3.1665. Min Range: -3.1665

Max Act: 3.0561. Min Act: -0.1700

Data Index: 1229714 (C4 (Web Text))

Max Activating Token Index: 826

Text #14

Max Range: 3.1665. Min Range: -3.1665

Max Act: 3.0719. Min Act: -0.1700

Data Index: 808675 (C4 (Web Text))

Max Activating Token Index: 686

Text #15

Max Range: 3.1665. Min Range: -3.1665

Max Act: 3.0561. Min Act: -0.1700

Data Index: 622565 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 3.1665. Min Range: -3.1665

Max Act: 3.0245. Min Act: -0.1700

Data Index: 1067184 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 3.1665. Min Range: -3.1665

Max Act: 3.0087. Min Act: -0.1700

Data Index: 836722 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 3.1665. Min Range: -3.1665

Max Act: 3.0245. Min Act: -0.1700

Data Index: 577378 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 3.1665. Min Range: -3.1665

Max Act: 3.0403. Min Act: -0.1700

Data Index: 153908 (C4 (Web Text))

Max Activating Token Index: 475