Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1692 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.4822. Min Range: -5.4822

Max Act: 5.4822. Min Act: -0.1700

Data Index: 119470 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 5.4822. Min Range: -5.4822

Max Act: 5.2947. Min Act: -0.1700

Data Index: 827854 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 5.4822. Min Range: -5.4822

Max Act: 5.2322. Min Act: -0.1700

Data Index: 865225 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 5.4822. Min Range: -5.4822

Max Act: 5.2322. Min Act: -0.1700

Data Index: 176022 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 5.4822. Min Range: -5.4822

Max Act: 5.2009. Min Act: -0.1700

Data Index: 37865 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 5.4822. Min Range: -5.4822

Max Act: 5.1384. Min Act: -0.1700

Data Index: 1047356 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 5.4822. Min Range: -5.4822

Max Act: 5.1072. Min Act: -0.1700

Data Index: 897639 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 5.4822. Min Range: -5.4822

Max Act: 5.1384. Min Act: -0.1700

Data Index: 218001 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 5.4822. Min Range: -5.4822

Max Act: 5.0759. Min Act: -0.1700

Data Index: 1152348 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 5.4822. Min Range: -5.4822

Max Act: 5.1384. Min Act: -0.1700

Data Index: 867166 (C4 (Web Text))

Max Activating Token Index: 531

Text #10

Max Range: 5.4822. Min Range: -5.4822

Max Act: 5.0759. Min Act: -0.1700

Data Index: 299817 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 5.4822. Min Range: -5.4822

Max Act: 5.1072. Min Act: -0.1700

Data Index: 259978 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 5.4822. Min Range: -5.4822

Max Act: 5.0134. Min Act: -0.1700

Data Index: 32641 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 5.4822. Min Range: -5.4822

Max Act: 5.0447. Min Act: -0.1700

Data Index: 838411 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 5.4822. Min Range: -5.4822

Max Act: 5.0447. Min Act: -0.1700

Data Index: 22276 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 5.4822. Min Range: -5.4822

Max Act: 4.9822. Min Act: -0.1700

Data Index: 813076 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 5.4822. Min Range: -5.4822

Max Act: 5.0447. Min Act: -0.1700

Data Index: 1117699 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 5.4822. Min Range: -5.4822

Max Act: 5.0447. Min Act: -0.1700

Data Index: 973042 (C4 (Web Text))

Max Activating Token Index: 759

Text #18

Max Range: 5.4822. Min Range: -5.4822

Max Act: 4.9822. Min Act: -0.1700

Data Index: 344385 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 5.4822. Min Range: -5.4822

Max Act: 5.0134. Min Act: -0.1700

Data Index: 301799 (C4 (Web Text))

Max Activating Token Index: 212