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

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

Neuron 494 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2992. Min Range: -5.2992

Max Act: 5.2992. Min Act: -0.1700

Data Index: 704567 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 5.2992. Min Range: -5.2992

Max Act: 5.2680. Min Act: -0.1700

Data Index: 522735 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 5.2992. Min Range: -5.2992

Max Act: 5.2055. Min Act: -0.1700

Data Index: 533232 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 5.2992. Min Range: -5.2992

Max Act: 5.0180. Min Act: -0.1700

Data Index: 848271 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 5.2992. Min Range: -5.2992

Max Act: 5.0805. Min Act: -0.1700

Data Index: 25845 (C4 (Web Text))

Max Activating Token Index: 244

Text #5

Max Range: 5.2992. Min Range: -5.2992

Max Act: 5.1117. Min Act: -0.1700

Data Index: 514954 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 5.2992. Min Range: -5.2992

Max Act: 5.1117. Min Act: -0.1700

Data Index: 465317 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 5.2992. Min Range: -5.2992

Max Act: 5.0805. Min Act: -0.1700

Data Index: 172262 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 5.2992. Min Range: -5.2992

Max Act: 5.1430. Min Act: -0.1700

Data Index: 338837 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 5.2992. Min Range: -5.2992

Max Act: 5.0180. Min Act: -0.1700

Data Index: 777396 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 5.2992. Min Range: -5.2992

Max Act: 5.0805. Min Act: -0.1699

Data Index: 299880 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 5.2992. Min Range: -5.2992

Max Act: 5.0492. Min Act: -0.1700

Data Index: 834109 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 5.2992. Min Range: -5.2992

Max Act: 5.0180. Min Act: -0.1700

Data Index: 483495 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 5.2992. Min Range: -5.2992

Max Act: 5.0492. Min Act: -0.1700

Data Index: 227890 (C4 (Web Text))

Max Activating Token Index: 758

Text #14

Max Range: 5.2992. Min Range: -5.2992

Max Act: 5.0492. Min Act: -0.1700

Data Index: 1085033 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 5.2992. Min Range: -5.2992

Max Act: 5.0180. Min Act: -0.1700

Data Index: 1205875 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 5.2992. Min Range: -5.2992

Max Act: 5.0492. Min Act: -0.1700

Data Index: 1262735 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 5.2992. Min Range: -5.2992

Max Act: 4.9867. Min Act: -0.1700

Data Index: 299818 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 5.2992. Min Range: -5.2992

Max Act: 4.9867. Min Act: -0.1700

Data Index: 1071396 (C4 (Web Text))

Max Activating Token Index: 163

Text #19

Max Range: 5.2992. Min Range: -5.2992

Max Act: 5.0180. Min Act: -0.1700

Data Index: 36637 (C4 (Web Text))

Max Activating Token Index: 348