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

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

Neuron 2025 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: 3.6582. Min Range: -3.6582

Max Act: 3.6269. Min Act: -0.1700

Data Index: 229480 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 3.6582. Min Range: -3.6582

Max Act: 3.6582. Min Act: -0.1700

Data Index: 391560 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 3.6582. Min Range: -3.6582

Max Act: 3.4702. Min Act: -0.1700

Data Index: 497370 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 3.6582. Min Range: -3.6582

Max Act: 3.5016. Min Act: -0.1700

Data Index: 1263811 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 3.6582. Min Range: -3.6582

Max Act: 3.5016. Min Act: -0.1700

Data Index: 1239060 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 3.6582. Min Range: -3.6582

Max Act: 3.4702. Min Act: -0.1700

Data Index: 1251738 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 3.6582. Min Range: -3.6582

Max Act: 3.4702. Min Act: -0.1700

Data Index: 1053646 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 3.6582. Min Range: -3.6582

Max Act: 3.4075. Min Act: -0.1700

Data Index: 238314 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 3.6582. Min Range: -3.6582

Max Act: 3.3604. Min Act: -0.1700

Data Index: 843421 (C4 (Web Text))

Max Activating Token Index: 1018

Text #9

Max Range: 3.6582. Min Range: -3.6582

Max Act: 3.3447. Min Act: -0.1700

Data Index: 484106 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 3.6582. Min Range: -3.6582

Max Act: 3.3918. Min Act: -0.1700

Data Index: 303881 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 3.6582. Min Range: -3.6582

Max Act: 3.3447. Min Act: -0.1700

Data Index: 637260 (C4 (Web Text))

Max Activating Token Index: 519

Text #12

Max Range: 3.6582. Min Range: -3.6582

Max Act: 3.3447. Min Act: -0.1700

Data Index: 1260598 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 3.6582. Min Range: -3.6582

Max Act: 3.3604. Min Act: -0.1700

Data Index: 892264 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 3.6582. Min Range: -3.6582

Max Act: 3.3761. Min Act: -0.1700

Data Index: 858049 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 3.6582. Min Range: -3.6582

Max Act: 3.3447. Min Act: -0.1700

Data Index: 556265 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 3.6582. Min Range: -3.6582

Max Act: 3.3291. Min Act: -0.1700

Data Index: 953929 (C4 (Web Text))

Max Activating Token Index: 733

Text #17

Max Range: 3.6582. Min Range: -3.6582

Max Act: 3.2819. Min Act: -0.1700

Data Index: 1251456 (C4 (Web Text))

Max Activating Token Index: 794

Text #18

Max Range: 3.6582. Min Range: -3.6582

Max Act: 3.2819. Min Act: -0.1700

Data Index: 995715 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 3.6582. Min Range: -3.6582

Max Act: 3.3134. Min Act: -0.1700

Data Index: 230488 (C4 (Web Text))

Max Activating Token Index: 23