Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 277 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.0578. Min Range: -4.0578
Max Act: 4.0578. Min Act: -0.1700
Data Index: 1597041 (Python Code)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0578. Min Range: -4.0578
Max Act: 4.0578. Min Act: -0.1700
Data Index: 1587484 (Python Code)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0578. Min Range: -4.0578
Max Act: 4.0578. Min Act: -0.1700
Data Index: 1400872 (Python Code)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0578. Min Range: -4.0578
Max Act: 4.0578. Min Act: -0.1700
Data Index: 1490588 (Python Code)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0578. Min Range: -4.0578
Max Act: 4.0265. Min Act: -0.1700
Data Index: 1426577 (Python Code)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0578. Min Range: -4.0578
Max Act: 3.9640. Min Act: -0.1700
Data Index: 1366317 (Python Code)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0578. Min Range: -4.0578
Max Act: 3.9953. Min Act: -0.1700
Data Index: 1639312 (Python Code)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0578. Min Range: -4.0578
Max Act: 3.9640. Min Act: -0.1700
Data Index: 1451726 (Python Code)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0578. Min Range: -4.0578
Max Act: 3.9953. Min Act: -0.1700
Data Index: 1401719 (Python Code)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0578. Min Range: -4.0578
Max Act: 3.9640. Min Act: -0.1700
Data Index: 1389487 (Python Code)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0578. Min Range: -4.0578
Max Act: 3.9953. Min Act: -0.1700
Data Index: 1639635 (Python Code)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0578. Min Range: -4.0578
Max Act: 3.9953. Min Act: -0.1700
Data Index: 1626821 (Python Code)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0578. Min Range: -4.0578
Max Act: 3.9327. Min Act: -0.1700
Data Index: 1541668 (Python Code)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0578. Min Range: -4.0578
Max Act: 3.9327. Min Act: -0.1700
Data Index: 1431498 (Python Code)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0578. Min Range: -4.0578
Max Act: 3.9640. Min Act: -0.1700
Data Index: 1435887 (Python Code)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0578. Min Range: -4.0578
Max Act: 3.9640. Min Act: -0.1700
Data Index: 1557967 (Python Code)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0578. Min Range: -4.0578
Max Act: 3.9015. Min Act: -0.1700
Data Index: 1550017 (Python Code)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0578. Min Range: -4.0578
Max Act: 3.9640. Min Act: -0.1700
Data Index: 1449934 (Python Code)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0578. Min Range: -4.0578
Max Act: 3.9327. Min Act: -0.1700
Data Index: 1593601 (Python Code)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0578. Min Range: -4.0578
Max Act: 3.9015. Min Act: -0.1700
Data Index: 1457397 (Python Code)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #19