Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2904 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9941. Min Range: -1.9941
Max Act: 1.9941. Min Act: -0.1682
Data Index: 807486 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9941. Min Range: -1.9941
Max Act: 1.9007. Min Act: -0.1700
Data Index: 6916323 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9941. Min Range: -1.9941
Max Act: 1.8494. Min Act: -0.1700
Data Index: 4749521 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9941. Min Range: -1.9941
Max Act: 1.8408. Min Act: -0.1700
Data Index: 7895547 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9941. Min Range: -1.9941
Max Act: 1.8065. Min Act: -0.1700
Data Index: 5109698 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9941. Min Range: -1.9941
Max Act: 1.7979. Min Act: -0.1700
Data Index: 2286048 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9941. Min Range: -1.9941
Max Act: 1.7979. Min Act: -0.1700
Data Index: 2815051 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9941. Min Range: -1.9941
Max Act: 1.7979. Min Act: -0.1700
Data Index: 1592657 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9941. Min Range: -1.9941
Max Act: 1.7979. Min Act: -0.1700
Data Index: 2156763 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9941. Min Range: -1.9941
Max Act: 1.7893. Min Act: -0.1700
Data Index: 5474052 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9941. Min Range: -1.9941
Max Act: 1.7807. Min Act: -0.1700
Data Index: 4716924 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9941. Min Range: -1.9941
Max Act: 1.7721. Min Act: -0.1700
Data Index: 4484255 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9941. Min Range: -1.9941
Max Act: 1.7721. Min Act: -0.1700
Data Index: 2415571 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9941. Min Range: -1.9941
Max Act: 1.7721. Min Act: -0.1700
Data Index: 706706 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9941. Min Range: -1.9941
Max Act: 1.7634. Min Act: -0.1700
Data Index: 4117994 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9941. Min Range: -1.9941
Max Act: 1.7721. Min Act: -0.1700
Data Index: 5972718 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9941. Min Range: -1.9941
Max Act: 1.7721. Min Act: -0.1700
Data Index: 7567690 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9941. Min Range: -1.9941
Max Act: 1.7634. Min Act: -0.1700
Data Index: 7092826 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9941. Min Range: -1.9941
Max Act: 1.7634. Min Act: -0.1699
Data Index: 7186153 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9941. Min Range: -1.9941
Max Act: 1.7548. Min Act: -0.1700
Data Index: 4166354 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19