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

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

Neuron 1752 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3704. Min Range: -3.3704

Max Act: 3.3704. Min Act: -0.1700

Data Index: 644855 (C4 (Web Text))

Max Activating Token Index: 709

Text #1

Max Range: 3.3704. Min Range: -3.3704

Max Act: 3.3704. Min Act: -0.1700

Data Index: 39921 (C4 (Web Text))

Max Activating Token Index: 706

Text #2

Max Range: 3.3704. Min Range: -3.3704

Max Act: 3.3390. Min Act: -0.1700

Data Index: 175513 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 3.3704. Min Range: -3.3704

Max Act: 3.3233. Min Act: -0.1700

Data Index: 72401 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 3.3704. Min Range: -3.3704

Max Act: 3.3233. Min Act: -0.1700

Data Index: 185224 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 3.3704. Min Range: -3.3704

Max Act: 3.2919. Min Act: -0.1700

Data Index: 643345 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 3.3704. Min Range: -3.3704

Max Act: 3.2762. Min Act: -0.1700

Data Index: 721641 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 3.3704. Min Range: -3.3704

Max Act: 3.2448. Min Act: -0.1700

Data Index: 912407 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 3.3704. Min Range: -3.3704

Max Act: 3.2448. Min Act: -0.1700

Data Index: 1261782 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 3.3704. Min Range: -3.3704

Max Act: 3.2605. Min Act: -0.1700

Data Index: 1231470 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 3.3704. Min Range: -3.3704

Max Act: 3.2448. Min Act: -0.1700

Data Index: 268984 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 3.3704. Min Range: -3.3704

Max Act: 3.2448. Min Act: -0.1700

Data Index: 835875 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 3.3704. Min Range: -3.3704

Max Act: 3.2291. Min Act: -0.1700

Data Index: 881335 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 3.3704. Min Range: -3.3704

Max Act: 3.2291. Min Act: -0.1700

Data Index: 20009 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 3.3704. Min Range: -3.3704

Max Act: 3.2133. Min Act: -0.1700

Data Index: 1280053 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 3.3704. Min Range: -3.3704

Max Act: 3.1976. Min Act: -0.1700

Data Index: 1061067 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 3.3704. Min Range: -3.3704

Max Act: 3.1819. Min Act: -0.1700

Data Index: 251537 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 3.3704. Min Range: -3.3704

Max Act: 3.1819. Min Act: -0.1700

Data Index: 233900 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 3.3704. Min Range: -3.3704

Max Act: 3.1819. Min Act: -0.1700

Data Index: 737568 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 3.3704. Min Range: -3.3704

Max Act: 3.1819. Min Act: -0.1700

Data Index: 597622 (C4 (Web Text))

Max Activating Token Index: 755