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

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

Neuron 1714 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6893. Min Range: -3.6893

Max Act: 3.6893. Min Act: -0.1700

Data Index: 999971 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 3.6893. Min Range: -3.6893

Max Act: 3.6424. Min Act: -0.1700

Data Index: 720785 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 3.6893. Min Range: -3.6893

Max Act: 3.6424. Min Act: -0.1700

Data Index: 520925 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 3.6893. Min Range: -3.6893

Max Act: 3.6424. Min Act: -0.1700

Data Index: 562647 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 3.6893. Min Range: -3.6893

Max Act: 3.6267. Min Act: -0.1700

Data Index: 750967 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 3.6893. Min Range: -3.6893

Max Act: 3.6111. Min Act: -0.1700

Data Index: 1167022 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 3.6893. Min Range: -3.6893

Max Act: 3.6267. Min Act: -0.1700

Data Index: 914806 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 3.6893. Min Range: -3.6893

Max Act: 3.6111. Min Act: -0.1700

Data Index: 782781 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 3.6893. Min Range: -3.6893

Max Act: 3.6111. Min Act: -0.1700

Data Index: 955943 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 3.6893. Min Range: -3.6893

Max Act: 3.5954. Min Act: -0.1700

Data Index: 516963 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 3.6893. Min Range: -3.6893

Max Act: 3.5954. Min Act: -0.1700

Data Index: 1019716 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 3.6893. Min Range: -3.6893

Max Act: 3.5797. Min Act: -0.1700

Data Index: 916254 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 3.6893. Min Range: -3.6893

Max Act: 3.5797. Min Act: -0.1700

Data Index: 1237091 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 3.6893. Min Range: -3.6893

Max Act: 3.5797. Min Act: -0.1700

Data Index: 968027 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 3.6893. Min Range: -3.6893

Max Act: 3.5797. Min Act: -0.1700

Data Index: 1316420 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 3.6893. Min Range: -3.6893

Max Act: 3.5797. Min Act: -0.1700

Data Index: 16067 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 3.6893. Min Range: -3.6893

Max Act: 3.5641. Min Act: -0.1700

Data Index: 208453 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 3.6893. Min Range: -3.6893

Max Act: 3.5641. Min Act: -0.1700

Data Index: 386767 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 3.6893. Min Range: -3.6893

Max Act: 3.5641. Min Act: -0.1700

Data Index: 40210 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 3.6893. Min Range: -3.6893

Max Act: 3.5484. Min Act: -0.1700

Data Index: 323660 (C4 (Web Text))

Max Activating Token Index: 282