Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1907 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.5840. Min Range: -2.5840
Max Act: 2.5840. Min Act: -0.1700
Data Index: 1050462 (C4 (Web Text))
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5840. Min Range: -2.5840
Max Act: 2.5194. Min Act: -0.1700
Data Index: 1213281 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5840. Min Range: -2.5840
Max Act: 2.5033. Min Act: -0.1700
Data Index: 57915 (C4 (Web Text))
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5840. Min Range: -2.5840
Max Act: 2.4871. Min Act: -0.1700
Data Index: 811411 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5840. Min Range: -2.5840
Max Act: 2.4708. Min Act: -0.1700
Data Index: 1513311 (Python Code)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5840. Min Range: -2.5840
Max Act: 2.5033. Min Act: -0.1700
Data Index: 811806 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5840. Min Range: -2.5840
Max Act: 2.4708. Min Act: -0.1700
Data Index: 884440 (C4 (Web Text))
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5840. Min Range: -2.5840
Max Act: 2.4546. Min Act: -0.1700
Data Index: 1382858 (Python Code)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5840. Min Range: -2.5840
Max Act: 2.4384. Min Act: -0.1700
Data Index: 1647903 (Python Code)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5840. Min Range: -2.5840
Max Act: 2.4871. Min Act: -0.1700
Data Index: 1398976 (Python Code)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5840. Min Range: -2.5840
Max Act: 2.4708. Min Act: -0.1700
Data Index: 823928 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5840. Min Range: -2.5840
Max Act: 2.4546. Min Act: -0.1700
Data Index: 815575 (C4 (Web Text))
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5840. Min Range: -2.5840
Max Act: 2.4708. Min Act: -0.1700
Data Index: 1205148 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5840. Min Range: -2.5840
Max Act: 2.4384. Min Act: -0.1700
Data Index: 121506 (C4 (Web Text))
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5840. Min Range: -2.5840
Max Act: 2.4384. Min Act: -0.1700
Data Index: 149178 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5840. Min Range: -2.5840
Max Act: 2.4384. Min Act: -0.1700
Data Index: 1457945 (Python Code)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5840. Min Range: -2.5840
Max Act: 2.4546. Min Act: -0.1700
Data Index: 1547749 (Python Code)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5840. Min Range: -2.5840
Max Act: 2.4384. Min Act: -0.1700
Data Index: 1552447 (Python Code)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5840. Min Range: -2.5840
Max Act: 2.4384. Min Act: -0.1700
Data Index: 1578574 (Python Code)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5840. Min Range: -2.5840
Max Act: 2.4384. Min Act: -0.1700
Data Index: 1624545 (Python Code)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #19