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

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

Neuron 771 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: 3.9763. Min Range: -3.9763

Max Act: 3.9763. Min Act: -0.1700

Data Index: 221227 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 3.9763. Min Range: -3.9763

Max Act: 3.9138. Min Act: -0.1700

Data Index: 496304 (C4 (Web Text))

Max Activating Token Index: 547

Text #2

Max Range: 3.9763. Min Range: -3.9763

Max Act: 3.8512. Min Act: -0.1700

Data Index: 1077109 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 3.9763. Min Range: -3.9763

Max Act: 3.7887. Min Act: -0.1700

Data Index: 60438 (C4 (Web Text))

Max Activating Token Index: 806

Text #4

Max Range: 3.9763. Min Range: -3.9763

Max Act: 3.7887. Min Act: -0.1700

Data Index: 295800 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 3.9763. Min Range: -3.9763

Max Act: 3.7261. Min Act: -0.1700

Data Index: 460823 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 3.9763. Min Range: -3.9763

Max Act: 3.6948. Min Act: -0.1700

Data Index: 315247 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 3.9763. Min Range: -3.9763

Max Act: 3.6322. Min Act: -0.1700

Data Index: 1303124 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 3.9763. Min Range: -3.9763

Max Act: 3.5383. Min Act: -0.1700

Data Index: 947156 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 3.9763. Min Range: -3.9763

Max Act: 3.6322. Min Act: -0.1700

Data Index: 255548 (C4 (Web Text))

Max Activating Token Index: 757

Text #10

Max Range: 3.9763. Min Range: -3.9763

Max Act: 3.5539. Min Act: -0.1700

Data Index: 1306737 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 3.9763. Min Range: -3.9763

Max Act: 3.5852. Min Act: -0.1700

Data Index: 825685 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 3.9763. Min Range: -3.9763

Max Act: 3.5069. Min Act: -0.1700

Data Index: 777680 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 3.9763. Min Range: -3.9763

Max Act: 3.5539. Min Act: -0.1700

Data Index: 443555 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 3.9763. Min Range: -3.9763

Max Act: 3.5069. Min Act: -0.1700

Data Index: 1173371 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 3.9763. Min Range: -3.9763

Max Act: 3.5539. Min Act: -0.1700

Data Index: 1117310 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 3.9763. Min Range: -3.9763

Max Act: 3.4599. Min Act: -0.1700

Data Index: 1195078 (C4 (Web Text))

Max Activating Token Index: 1003

Text #17

Max Range: 3.9763. Min Range: -3.9763

Max Act: 3.4442. Min Act: -0.1700

Data Index: 107183 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 3.9763. Min Range: -3.9763

Max Act: 3.4599. Min Act: -0.1700

Data Index: 990722 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 3.9763. Min Range: -3.9763

Max Act: 3.3815. Min Act: -0.1700

Data Index: 760126 (C4 (Web Text))

Max Activating Token Index: 792