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

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

Neuron 396 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9580. Min Range: -3.9580

Max Act: 3.9267. Min Act: -0.1700

Data Index: 1322446 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 3.9580. Min Range: -3.9580

Max Act: 3.9580. Min Act: -0.1700

Data Index: 976100 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 3.9580. Min Range: -3.9580

Max Act: 3.9267. Min Act: -0.1700

Data Index: 399454 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 3.9580. Min Range: -3.9580

Max Act: 3.8642. Min Act: -0.1700

Data Index: 45611 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 3.9580. Min Range: -3.9580

Max Act: 3.8329. Min Act: -0.1700

Data Index: 1259493 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 3.9580. Min Range: -3.9580

Max Act: 3.8329. Min Act: -0.1700

Data Index: 79060 (C4 (Web Text))

Max Activating Token Index: 474

Text #6

Max Range: 3.9580. Min Range: -3.9580

Max Act: 3.8329. Min Act: -0.1700

Data Index: 1265892 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 3.9580. Min Range: -3.9580

Max Act: 3.8016. Min Act: -0.1700

Data Index: 829823 (C4 (Web Text))

Max Activating Token Index: 744

Text #8

Max Range: 3.9580. Min Range: -3.9580

Max Act: 3.8642. Min Act: -0.1700

Data Index: 880431 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 3.9580. Min Range: -3.9580

Max Act: 3.8016. Min Act: -0.1700

Data Index: 926655 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 3.9580. Min Range: -3.9580

Max Act: 3.8016. Min Act: -0.1700

Data Index: 263296 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 3.9580. Min Range: -3.9580

Max Act: 3.7390. Min Act: -0.1700

Data Index: 393463 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 3.9580. Min Range: -3.9580

Max Act: 3.7703. Min Act: -0.1700

Data Index: 1037160 (C4 (Web Text))

Max Activating Token Index: 558

Text #13

Max Range: 3.9580. Min Range: -3.9580

Max Act: 3.7703. Min Act: -0.1700

Data Index: 1083104 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 3.9580. Min Range: -3.9580

Max Act: 3.7703. Min Act: -0.1700

Data Index: 145593 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 3.9580. Min Range: -3.9580

Max Act: 3.7703. Min Act: -0.1700

Data Index: 899193 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 3.9580. Min Range: -3.9580

Max Act: 3.7703. Min Act: -0.1700

Data Index: 1127276 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 3.9580. Min Range: -3.9580

Max Act: 3.7703. Min Act: -0.1700

Data Index: 920256 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 3.9580. Min Range: -3.9580

Max Act: 3.7390. Min Act: -0.1700

Data Index: 370063 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 3.9580. Min Range: -3.9580

Max Act: 3.7390. Min Act: -0.1700

Data Index: 924959 (C4 (Web Text))

Max Activating Token Index: 861