Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 502 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2993. Min Range: -6.2993
Max Act: 6.2993. Min Act: -0.1700
Data Index: 7285411 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2993. Min Range: -6.2993
Max Act: 6.2993. Min Act: -0.1700
Data Index: 5617931 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2993. Min Range: -6.2993
Max Act: 6.2055. Min Act: -0.1700
Data Index: 5473965 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2993. Min Range: -6.2993
Max Act: 6.2055. Min Act: -0.1700
Data Index: 8037658 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2993. Min Range: -6.2993
Max Act: 6.1743. Min Act: -0.1699
Data Index: 6774752 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2993. Min Range: -6.2993
Max Act: 6.1430. Min Act: -0.1700
Data Index: 1331705 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2993. Min Range: -6.2993
Max Act: 6.1118. Min Act: -0.1700
Data Index: 567494 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2993. Min Range: -6.2993
Max Act: 6.1118. Min Act: -0.1700
Data Index: 8771481 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2993. Min Range: -6.2993
Max Act: 6.1118. Min Act: -0.1699
Data Index: 1944664 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2993. Min Range: -6.2993
Max Act: 6.0805. Min Act: -0.1699
Data Index: 3127128 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2993. Min Range: -6.2993
Max Act: 6.0805. Min Act: -0.1700
Data Index: 6062032 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2993. Min Range: -6.2993
Max Act: 6.0805. Min Act: -0.1700
Data Index: 5919353 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2993. Min Range: -6.2993
Max Act: 6.0805. Min Act: -0.1700
Data Index: 3833688 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2993. Min Range: -6.2993
Max Act: 6.0805. Min Act: -0.1697
Data Index: 4711026 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2993. Min Range: -6.2993
Max Act: 6.0805. Min Act: -0.1700
Data Index: 7061895 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2993. Min Range: -6.2993
Max Act: 6.0493. Min Act: -0.1700
Data Index: 5851624 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2993. Min Range: -6.2993
Max Act: 6.0493. Min Act: -0.1700
Data Index: 5916626 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2993. Min Range: -6.2993
Max Act: 6.0493. Min Act: -0.1700
Data Index: 1095627 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2993. Min Range: -6.2993
Max Act: 6.0493. Min Act: -0.1700
Data Index: 5243183 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2993. Min Range: -6.2993
Max Act: 6.0493. Min Act: -0.1700
Data Index: 6361946 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #19