Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4047 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0857. Min Range: -2.0857
Max Act: 2.0857. Min Act: -0.1613
Data Index: 4663469 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0857. Min Range: -2.0857
Max Act: 1.9677. Min Act: -0.1700
Data Index: 451932 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0857. Min Range: -2.0857
Max Act: 1.9507. Min Act: -0.1681
Data Index: 8231136 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0857. Min Range: -2.0857
Max Act: 1.9337. Min Act: -0.1700
Data Index: 1210269 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0857. Min Range: -2.0857
Max Act: 1.9167. Min Act: -0.1700
Data Index: 6549672 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0857. Min Range: -2.0857
Max Act: 1.8997. Min Act: -0.1700
Data Index: 4472939 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0857. Min Range: -2.0857
Max Act: 1.9167. Min Act: -0.1700
Data Index: 4166374 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0857. Min Range: -2.0857
Max Act: 1.8826. Min Act: -0.1690
Data Index: 5891942 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0857. Min Range: -2.0857
Max Act: 1.8826. Min Act: -0.1700
Data Index: 7471312 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0857. Min Range: -2.0857
Max Act: 1.8826. Min Act: -0.1700
Data Index: 4566502 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0857. Min Range: -2.0857
Max Act: 1.8997. Min Act: -0.1619
Data Index: 4320119 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0857. Min Range: -2.0857
Max Act: 1.8655. Min Act: -0.1689
Data Index: 7607699 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0857. Min Range: -2.0857
Max Act: 1.8826. Min Act: -0.1671
Data Index: 6641648 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0857. Min Range: -2.0857
Max Act: 1.8655. Min Act: -0.1681
Data Index: 3603352 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0857. Min Range: -2.0857
Max Act: 1.8826. Min Act: -0.1698
Data Index: 1191494 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0857. Min Range: -2.0857
Max Act: 1.8655. Min Act: -0.1699
Data Index: 2913458 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0857. Min Range: -2.0857
Max Act: 1.8484. Min Act: -0.1700
Data Index: 2575058 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0857. Min Range: -2.0857
Max Act: 1.8484. Min Act: -0.1700
Data Index: 2072238 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0857. Min Range: -2.0857
Max Act: 1.8484. Min Act: -0.1697
Data Index: 3689875 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0857. Min Range: -2.0857
Max Act: 1.8484. Min Act: -0.1698
Data Index: 4845468 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19