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

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

Neuron 1929 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.7625. Min Act: -0.1700

Data Index: 361455 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.7156. Min Act: -0.1700

Data Index: 32058 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.6843. Min Act: -0.1700

Data Index: 343407 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.6530. Min Act: -0.1700

Data Index: 1174592 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.6530. Min Act: -0.1700

Data Index: 898895 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.6686. Min Act: -0.1700

Data Index: 574770 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.6217. Min Act: -0.1700

Data Index: 1005868 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.6217. Min Act: -0.1700

Data Index: 496640 (C4 (Web Text))

Max Activating Token Index: 720

Text #8

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.6373. Min Act: -0.1700

Data Index: 234052 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.6217. Min Act: -0.1700

Data Index: 514855 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.6217. Min Act: -0.1700

Data Index: 1160542 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.6373. Min Act: -0.1700

Data Index: 1322083 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.5590. Min Act: -0.1700

Data Index: 1123794 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.5904. Min Act: -0.1700

Data Index: 796130 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.6060. Min Act: -0.1700

Data Index: 781439 (C4 (Web Text))

Max Activating Token Index: 990

Text #15

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.5747. Min Act: -0.1700

Data Index: 1169218 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.5904. Min Act: -0.1700

Data Index: 1066200 (C4 (Web Text))

Max Activating Token Index: 892

Text #17

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.5590. Min Act: -0.1700

Data Index: 333314 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.5747. Min Act: -0.1700

Data Index: 1322930 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.5434. Min Act: -0.1700

Data Index: 1142772 (C4 (Web Text))

Max Activating Token Index: 168