Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 161 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.0056. Min Range: -3.0056
Max Act: 3.0056. Min Act: -0.1700
Data Index: 1238383 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0056. Min Range: -3.0056
Max Act: 2.9740. Min Act: -0.1700
Data Index: 1352142 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0056. Min Range: -3.0056
Max Act: 2.9265. Min Act: -0.1700
Data Index: 515293 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0056. Min Range: -3.0056
Max Act: 2.9106. Min Act: -0.1700
Data Index: 361388 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0056. Min Range: -3.0056
Max Act: 2.9265. Min Act: -0.1700
Data Index: 549336 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0056. Min Range: -3.0056
Max Act: 2.9265. Min Act: -0.1700
Data Index: 234577 (C4 (Web Text))
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0056. Min Range: -3.0056
Max Act: 2.9106. Min Act: -0.1700
Data Index: 719625 (C4 (Web Text))
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0056. Min Range: -3.0056
Max Act: 2.9106. Min Act: -0.1700
Data Index: 1117231 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0056. Min Range: -3.0056
Max Act: 2.8948. Min Act: -0.1700
Data Index: 1305086 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0056. Min Range: -3.0056
Max Act: 2.8948. Min Act: -0.1700
Data Index: 72643 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0056. Min Range: -3.0056
Max Act: 2.8948. Min Act: -0.1700
Data Index: 851366 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0056. Min Range: -3.0056
Max Act: 2.8630. Min Act: -0.1700
Data Index: 1314953 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0056. Min Range: -3.0056
Max Act: 2.8948. Min Act: -0.1700
Data Index: 1148994 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0056. Min Range: -3.0056
Max Act: 2.8789. Min Act: -0.1700
Data Index: 1107716 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0056. Min Range: -3.0056
Max Act: 2.8789. Min Act: -0.1700
Data Index: 888647 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0056. Min Range: -3.0056
Max Act: 2.8630. Min Act: -0.1700
Data Index: 342065 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0056. Min Range: -3.0056
Max Act: 2.8630. Min Act: -0.1700
Data Index: 780492 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0056. Min Range: -3.0056
Max Act: 2.8630. Min Act: -0.1700
Data Index: 1299642 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0056. Min Range: -3.0056
Max Act: 2.8630. Min Act: -0.1700
Data Index: 1277547 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0056. Min Range: -3.0056
Max Act: 2.8630. Min Act: -0.1700
Data Index: 494345 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19