Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 946 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.5859. Min Range: -2.5859
Max Act: 2.5859. Min Act: -0.1700
Data Index: 1551931 (Python Code)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5859. Min Range: -2.5859
Max Act: 2.5052. Min Act: -0.1700
Data Index: 1614057 (Python Code)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5859. Min Range: -2.5859
Max Act: 2.4890. Min Act: -0.1700
Data Index: 1100438 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5859. Min Range: -2.5859
Max Act: 2.4566. Min Act: -0.1700
Data Index: 1568919 (Python Code)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5859. Min Range: -2.5859
Max Act: 2.3751. Min Act: -0.1700
Data Index: 1167129 (C4 (Web Text))
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5859. Min Range: -2.5859
Max Act: 2.3751. Min Act: -0.1700
Data Index: 1049456 (C4 (Web Text))
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5859. Min Range: -2.5859
Max Act: 2.3587. Min Act: -0.1700
Data Index: 1415050 (Python Code)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5859. Min Range: -2.5859
Max Act: 2.3587. Min Act: -0.1700
Data Index: 1400965 (Python Code)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5859. Min Range: -2.5859
Max Act: 2.3587. Min Act: -0.1700
Data Index: 1574552 (Python Code)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5859. Min Range: -2.5859
Max Act: 2.3587. Min Act: -0.1700
Data Index: 1381142 (Python Code)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5859. Min Range: -2.5859
Max Act: 2.3587. Min Act: -0.1700
Data Index: 807064 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5859. Min Range: -2.5859
Max Act: 2.3587. Min Act: -0.1700
Data Index: 290916 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5859. Min Range: -2.5859
Max Act: 2.3587. Min Act: -0.1700
Data Index: 1515151 (Python Code)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5859. Min Range: -2.5859
Max Act: 2.3587. Min Act: -0.1700
Data Index: 1471102 (Python Code)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5859. Min Range: -2.5859
Max Act: 2.3587. Min Act: -0.1700
Data Index: 1654127 (Python Code)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5859. Min Range: -2.5859
Max Act: 2.3587. Min Act: -0.1700
Data Index: 1635549 (Python Code)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5859. Min Range: -2.5859
Max Act: 2.3587. Min Act: -0.1700
Data Index: 1395156 (Python Code)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5859. Min Range: -2.5859
Max Act: 2.3587. Min Act: -0.1700
Data Index: 1383484 (Python Code)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5859. Min Range: -2.5859
Max Act: 2.3587. Min Act: -0.1700
Data Index: 1616237 (Python Code)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5859. Min Range: -2.5859
Max Act: 2.3587. Min Act: -0.1700
Data Index: 1375686 (Python Code)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #19