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

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

Neuron 349 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: 3.3147. Min Range: -3.3147

Max Act: 3.3147. Min Act: -0.1700

Data Index: 387916 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 3.3147. Min Range: -3.3147

Max Act: 3.2833. Min Act: -0.1700

Data Index: 621647 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 3.3147. Min Range: -3.3147

Max Act: 3.2990. Min Act: -0.1700

Data Index: 1277526 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 3.3147. Min Range: -3.3147

Max Act: 3.2833. Min Act: -0.1700

Data Index: 512484 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 3.3147. Min Range: -3.3147

Max Act: 3.2519. Min Act: -0.1700

Data Index: 827733 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 3.3147. Min Range: -3.3147

Max Act: 3.2205. Min Act: -0.1700

Data Index: 1051951 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 3.3147. Min Range: -3.3147

Max Act: 3.2205. Min Act: -0.1700

Data Index: 495348 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 3.3147. Min Range: -3.3147

Max Act: 3.2205. Min Act: -0.1700

Data Index: 580671 (C4 (Web Text))

Max Activating Token Index: 547

Text #8

Max Range: 3.3147. Min Range: -3.3147

Max Act: 3.2205. Min Act: -0.1700

Data Index: 974268 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 3.3147. Min Range: -3.3147

Max Act: 3.2205. Min Act: -0.1700

Data Index: 435051 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 3.3147. Min Range: -3.3147

Max Act: 3.2047. Min Act: -0.1700

Data Index: 469126 (C4 (Web Text))

Max Activating Token Index: 102

Text #11

Max Range: 3.3147. Min Range: -3.3147

Max Act: 3.1890. Min Act: -0.1700

Data Index: 1304024 (C4 (Web Text))

Max Activating Token Index: 798

Text #12

Max Range: 3.3147. Min Range: -3.3147

Max Act: 3.1890. Min Act: -0.1700

Data Index: 868581 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 3.3147. Min Range: -3.3147

Max Act: 3.1733. Min Act: -0.1700

Data Index: 715707 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 3.3147. Min Range: -3.3147

Max Act: 3.1575. Min Act: -0.1700

Data Index: 973628 (C4 (Web Text))

Max Activating Token Index: 973

Text #15

Max Range: 3.3147. Min Range: -3.3147

Max Act: 3.1418. Min Act: -0.1700

Data Index: 251086 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 3.3147. Min Range: -3.3147

Max Act: 3.1733. Min Act: -0.1700

Data Index: 581745 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 3.3147. Min Range: -3.3147

Max Act: 3.2047. Min Act: -0.1700

Data Index: 650979 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 3.3147. Min Range: -3.3147

Max Act: 3.1733. Min Act: -0.1700

Data Index: 370235 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 3.3147. Min Range: -3.3147

Max Act: 3.1890. Min Act: -0.1700

Data Index: 614793 (C4 (Web Text))

Max Activating Token Index: 717