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

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

Neuron 336 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: 3.5974. Min Range: -3.5974

Max Act: 3.5818. Min Act: -0.1700

Data Index: 1215478 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 3.5974. Min Range: -3.5974

Max Act: 3.5818. Min Act: -0.1700

Data Index: 1200350 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 3.5974. Min Range: -3.5974

Max Act: 3.5661. Min Act: -0.1700

Data Index: 42524 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 3.5974. Min Range: -3.5974

Max Act: 3.5818. Min Act: -0.1700

Data Index: 1155386 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 3.5974. Min Range: -3.5974

Max Act: 3.5974. Min Act: -0.1700

Data Index: 998979 (C4 (Web Text))

Max Activating Token Index: 343

Text #5

Max Range: 3.5974. Min Range: -3.5974

Max Act: 3.5661. Min Act: -0.1700

Data Index: 839065 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 3.5974. Min Range: -3.5974

Max Act: 3.5504. Min Act: -0.1700

Data Index: 926879 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 3.5974. Min Range: -3.5974

Max Act: 3.5818. Min Act: -0.1700

Data Index: 805435 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 3.5974. Min Range: -3.5974

Max Act: 3.5661. Min Act: -0.1700

Data Index: 1137753 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 3.5974. Min Range: -3.5974

Max Act: 3.5661. Min Act: -0.1700

Data Index: 1315713 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 3.5974. Min Range: -3.5974

Max Act: 3.5504. Min Act: -0.1700

Data Index: 504576 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 3.5974. Min Range: -3.5974

Max Act: 3.5661. Min Act: -0.1700

Data Index: 784377 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 3.5974. Min Range: -3.5974

Max Act: 3.5348. Min Act: -0.1700

Data Index: 1302512 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 3.5974. Min Range: -3.5974

Max Act: 3.5191. Min Act: -0.1700

Data Index: 320166 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 3.5974. Min Range: -3.5974

Max Act: 3.5348. Min Act: -0.1700

Data Index: 157416 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 3.5974. Min Range: -3.5974

Max Act: 3.5348. Min Act: -0.1700

Data Index: 1133132 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 3.5974. Min Range: -3.5974

Max Act: 3.5504. Min Act: -0.1700

Data Index: 954825 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 3.5974. Min Range: -3.5974

Max Act: 3.5191. Min Act: -0.1700

Data Index: 280043 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 3.5974. Min Range: -3.5974

Max Act: 3.5348. Min Act: -0.1700

Data Index: 571027 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 3.5974. Min Range: -3.5974

Max Act: 3.4721. Min Act: -0.1700

Data Index: 243235 (C4 (Web Text))

Max Activating Token Index: 64