Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 726 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.2738. Min Range: -5.2738

Max Act: 5.2738. Min Act: -0.1700

Data Index: 238889 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 5.2738. Min Range: -5.2738

Max Act: 5.2425. Min Act: -0.1700

Data Index: 1076172 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 5.2738. Min Range: -5.2738

Max Act: 5.2269. Min Act: -0.1700

Data Index: 432796 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 5.2738. Min Range: -5.2738

Max Act: 5.1488. Min Act: -0.1700

Data Index: 997307 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 5.2738. Min Range: -5.2738

Max Act: 5.0238. Min Act: -0.1700

Data Index: 480992 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 5.2738. Min Range: -5.2738

Max Act: 5.0863. Min Act: -0.1700

Data Index: 1107603 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 5.2738. Min Range: -5.2738

Max Act: 5.0550. Min Act: -0.1700

Data Index: 480411 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 5.2738. Min Range: -5.2738

Max Act: 5.0238. Min Act: -0.1700

Data Index: 372726 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.9769. Min Act: -0.1700

Data Index: 434418 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 5.2738. Min Range: -5.2738

Max Act: 5.1019. Min Act: -0.1700

Data Index: 273424 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 5.2738. Min Range: -5.2738

Max Act: 5.1019. Min Act: -0.1700

Data Index: 135586 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.8987. Min Act: -0.1700

Data Index: 934018 (C4 (Web Text))

Max Activating Token Index: 954

Text #12

Max Range: 5.2738. Min Range: -5.2738

Max Act: 5.0081. Min Act: -0.1700

Data Index: 329027 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 5.2738. Min Range: -5.2738

Max Act: 5.1488. Min Act: -0.1700

Data Index: 748360 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.9144. Min Act: -0.1700

Data Index: 1086179 (C4 (Web Text))

Max Activating Token Index: 597

Text #15

Max Range: 5.2738. Min Range: -5.2738

Max Act: 5.0394. Min Act: -0.1700

Data Index: 1061947 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.9769. Min Act: -0.1700

Data Index: 359908 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 5.2738. Min Range: -5.2738

Max Act: 5.1644. Min Act: -0.1700

Data Index: 1091401 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.9769. Min Act: -0.1700

Data Index: 535891 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.9300. Min Act: -0.1700

Data Index: 22490 (C4 (Web Text))

Max Activating Token Index: 489