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

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

Neuron 448 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: 3.9143. Min Range: -3.9143

Max Act: 3.9143. Min Act: -0.1700

Data Index: 1172570 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.7892. Min Act: -0.1700

Data Index: 504527 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.7892. Min Act: -0.1700

Data Index: 555912 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.8362. Min Act: -0.1700

Data Index: 149203 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.7736. Min Act: -0.1700

Data Index: 392759 (C4 (Web Text))

Max Activating Token Index: 740

Text #5

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.8205. Min Act: -0.1700

Data Index: 123752 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.7736. Min Act: -0.1700

Data Index: 788623 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.7267. Min Act: -0.1700

Data Index: 165017 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.7736. Min Act: -0.1700

Data Index: 662637 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.7579. Min Act: -0.1700

Data Index: 790247 (C4 (Web Text))

Max Activating Token Index: 999

Text #10

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.7423. Min Act: -0.1700

Data Index: 420123 (C4 (Web Text))

Max Activating Token Index: 628

Text #11

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.8362. Min Act: -0.1700

Data Index: 453348 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.7423. Min Act: -0.1700

Data Index: 776073 (C4 (Web Text))

Max Activating Token Index: 309

Text #13

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.7110. Min Act: -0.1700

Data Index: 684299 (C4 (Web Text))

Max Activating Token Index: 548

Text #14

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.7267. Min Act: -0.1700

Data Index: 851799 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.7579. Min Act: -0.1700

Data Index: 440172 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.7267. Min Act: -0.1700

Data Index: 781899 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.6641. Min Act: -0.1700

Data Index: 909966 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.7267. Min Act: -0.1700

Data Index: 133684 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.7267. Min Act: -0.1700

Data Index: 995758 (C4 (Web Text))

Max Activating Token Index: 722