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

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

Neuron 598 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: 3.3421. Min Range: -3.3421

Max Act: 3.3421. Min Act: -0.1700

Data Index: 39343 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 3.3421. Min Range: -3.3421

Max Act: 3.2950. Min Act: -0.1700

Data Index: 710876 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 3.3421. Min Range: -3.3421

Max Act: 3.2636. Min Act: -0.1700

Data Index: 601355 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 3.3421. Min Range: -3.3421

Max Act: 3.2793. Min Act: -0.1700

Data Index: 206867 (C4 (Web Text))

Max Activating Token Index: 607

Text #4

Max Range: 3.3421. Min Range: -3.3421

Max Act: 3.2636. Min Act: -0.1700

Data Index: 106218 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 3.3421. Min Range: -3.3421

Max Act: 3.2479. Min Act: -0.1700

Data Index: 1101484 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 3.3421. Min Range: -3.3421

Max Act: 3.2793. Min Act: -0.1700

Data Index: 448760 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 3.3421. Min Range: -3.3421

Max Act: 3.2007. Min Act: -0.1700

Data Index: 842237 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 3.3421. Min Range: -3.3421

Max Act: 3.2007. Min Act: -0.1700

Data Index: 987301 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 3.3421. Min Range: -3.3421

Max Act: 3.2164. Min Act: -0.1700

Data Index: 474786 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 3.3421. Min Range: -3.3421

Max Act: 3.1692. Min Act: -0.1700

Data Index: 355276 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 3.3421. Min Range: -3.3421

Max Act: 3.2164. Min Act: -0.1700

Data Index: 467964 (C4 (Web Text))

Max Activating Token Index: 484

Text #12

Max Range: 3.3421. Min Range: -3.3421

Max Act: 3.1535. Min Act: -0.1700

Data Index: 763862 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 3.3421. Min Range: -3.3421

Max Act: 3.1850. Min Act: -0.1700

Data Index: 1110228 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 3.3421. Min Range: -3.3421

Max Act: 3.1692. Min Act: -0.1700

Data Index: 762628 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 3.3421. Min Range: -3.3421

Max Act: 3.1692. Min Act: -0.1700

Data Index: 763727 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 3.3421. Min Range: -3.3421

Max Act: 3.1692. Min Act: -0.1700

Data Index: 879220 (C4 (Web Text))

Max Activating Token Index: 249

Text #17

Max Range: 3.3421. Min Range: -3.3421

Max Act: 3.1535. Min Act: -0.1700

Data Index: 790414 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 3.3421. Min Range: -3.3421

Max Act: 3.1692. Min Act: -0.1700

Data Index: 718931 (C4 (Web Text))

Max Activating Token Index: 813

Text #19

Max Range: 3.3421. Min Range: -3.3421

Max Act: 3.1850. Min Act: -0.1700

Data Index: 264533 (C4 (Web Text))

Max Activating Token Index: 1016