Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4466 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9040. Min Range: -5.9040
Max Act: 5.9040. Min Act: -0.1700
Data Index: 4863290 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9040. Min Range: -5.9040
Max Act: 5.7165. Min Act: -0.1700
Data Index: 4145336 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9040. Min Range: -5.9040
Max Act: 5.6853. Min Act: -0.1700
Data Index: 400247 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9040. Min Range: -5.9040
Max Act: 5.6540. Min Act: -0.1700
Data Index: 5502045 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9040. Min Range: -5.9040
Max Act: 5.5915. Min Act: -0.1700
Data Index: 5828979 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9040. Min Range: -5.9040
Max Act: 5.5915. Min Act: -0.1700
Data Index: 5196150 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9040. Min Range: -5.9040
Max Act: 5.5603. Min Act: -0.1700
Data Index: 7436535 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9040. Min Range: -5.9040
Max Act: 5.5603. Min Act: -0.1700
Data Index: 1650634 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9040. Min Range: -5.9040
Max Act: 5.4978. Min Act: -0.1700
Data Index: 8379679 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9040. Min Range: -5.9040
Max Act: 5.4978. Min Act: -0.1700
Data Index: 8810953 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9040. Min Range: -5.9040
Max Act: 5.4665. Min Act: -0.1700
Data Index: 3970148 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9040. Min Range: -5.9040
Max Act: 5.4353. Min Act: -0.1700
Data Index: 3462597 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9040. Min Range: -5.9040
Max Act: 5.4353. Min Act: -0.1700
Data Index: 5534540 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9040. Min Range: -5.9040
Max Act: 5.4353. Min Act: -0.1700
Data Index: 7781558 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9040. Min Range: -5.9040
Max Act: 5.4353. Min Act: -0.1700
Data Index: 2759973 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9040. Min Range: -5.9040
Max Act: 5.4040. Min Act: -0.1700
Data Index: 1805092 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9040. Min Range: -5.9040
Max Act: 5.4040. Min Act: -0.1700
Data Index: 3708980 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9040. Min Range: -5.9040
Max Act: 5.4040. Min Act: -0.1700
Data Index: 265193 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9040. Min Range: -5.9040
Max Act: 5.3728. Min Act: -0.1700
Data Index: 6343875 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9040. Min Range: -5.9040
Max Act: 5.3728. Min Act: -0.1700
Data Index: 3455516 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19