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

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

Neuron 1960 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.2888. Min Act: -0.1700

Data Index: 24072 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.2574. Min Act: -0.1700

Data Index: 204293 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.1787. Min Act: -0.1700

Data Index: 974266 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.2416. Min Act: -0.1700

Data Index: 697994 (C4 (Web Text))

Max Activating Token Index: 5

Text #4

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.2102. Min Act: -0.1700

Data Index: 80028 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.2102. Min Act: -0.1700

Data Index: 112572 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.1945. Min Act: -0.1700

Data Index: 469974 (C4 (Web Text))

Max Activating Token Index: 823

Text #7

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.2102. Min Act: -0.1700

Data Index: 1262717 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.1945. Min Act: -0.1700

Data Index: 627896 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.1630. Min Act: -0.1700

Data Index: 939531 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.1787. Min Act: -0.1700

Data Index: 1164017 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.1630. Min Act: -0.1700

Data Index: 978790 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.1630. Min Act: -0.1700

Data Index: 353090 (C4 (Web Text))

Max Activating Token Index: 845

Text #13

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.1630. Min Act: -0.1700

Data Index: 509919 (C4 (Web Text))

Max Activating Token Index: 400

Text #14

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.1630. Min Act: -0.1700

Data Index: 6884 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.1630. Min Act: -0.1700

Data Index: 822477 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.1787. Min Act: -0.1700

Data Index: 768644 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.1945. Min Act: -0.1700

Data Index: 514636 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.1472. Min Act: -0.1700

Data Index: 871527 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.1472. Min Act: -0.1700

Data Index: 359553 (C4 (Web Text))

Max Activating Token Index: 582