Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3768 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1590. Min Range: -6.1590
Max Act: 6.1590. Min Act: -0.1700
Data Index: 7187196 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1590. Min Range: -6.1590
Max Act: 5.9090. Min Act: -0.1700
Data Index: 1695832 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1590. Min Range: -6.1590
Max Act: 5.8465. Min Act: -0.1700
Data Index: 4761040 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1590. Min Range: -6.1590
Max Act: 5.8152. Min Act: -0.1700
Data Index: 3778637 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1590. Min Range: -6.1590
Max Act: 5.8152. Min Act: -0.1700
Data Index: 7306628 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1590. Min Range: -6.1590
Max Act: 5.7840. Min Act: -0.1700
Data Index: 1113509 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1590. Min Range: -6.1590
Max Act: 5.7840. Min Act: -0.1700
Data Index: 2976497 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1590. Min Range: -6.1590
Max Act: 5.7527. Min Act: -0.1700
Data Index: 6098713 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1590. Min Range: -6.1590
Max Act: 5.7215. Min Act: -0.1700
Data Index: 4212864 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1590. Min Range: -6.1590
Max Act: 5.7215. Min Act: -0.1700
Data Index: 2477935 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1590. Min Range: -6.1590
Max Act: 5.6902. Min Act: -0.1700
Data Index: 3578240 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1590. Min Range: -6.1590
Max Act: 5.7215. Min Act: -0.1700
Data Index: 249474 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1590. Min Range: -6.1590
Max Act: 5.7215. Min Act: -0.1700
Data Index: 8074649 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1590. Min Range: -6.1590
Max Act: 5.7215. Min Act: -0.1700
Data Index: 2065778 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1590. Min Range: -6.1590
Max Act: 5.6590. Min Act: -0.1700
Data Index: 3730616 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1590. Min Range: -6.1590
Max Act: 5.6590. Min Act: -0.1700
Data Index: 8826188 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1590. Min Range: -6.1590
Max Act: 5.6902. Min Act: -0.1700
Data Index: 7820934 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1590. Min Range: -6.1590
Max Act: 5.6277. Min Act: -0.1700
Data Index: 2151194 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1590. Min Range: -6.1590
Max Act: 5.6277. Min Act: -0.1700
Data Index: 2163071 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1590. Min Range: -6.1590
Max Act: 5.5965. Min Act: -0.1700
Data Index: 3440780 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #19