Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2512 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3590. Min Range: -5.3590
Max Act: 5.3590. Min Act: -0.1700
Data Index: 5543918 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3590. Min Range: -5.3590
Max Act: 5.1715. Min Act: -0.1700
Data Index: 639804 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3590. Min Range: -5.3590
Max Act: 5.1403. Min Act: -0.1700
Data Index: 291192 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3590. Min Range: -5.3590
Max Act: 5.1090. Min Act: -0.1700
Data Index: 5145159 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3590. Min Range: -5.3590
Max Act: 5.0465. Min Act: -0.1700
Data Index: 5594840 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3590. Min Range: -5.3590
Max Act: 5.0778. Min Act: -0.1700
Data Index: 7152317 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3590. Min Range: -5.3590
Max Act: 5.0778. Min Act: -0.1700
Data Index: 6325015 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3590. Min Range: -5.3590
Max Act: 5.0465. Min Act: -0.1700
Data Index: 771931 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3590. Min Range: -5.3590
Max Act: 5.0778. Min Act: -0.1700
Data Index: 6425774 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3590. Min Range: -5.3590
Max Act: 5.0778. Min Act: -0.1700
Data Index: 2564602 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3590. Min Range: -5.3590
Max Act: 5.0465. Min Act: -0.1700
Data Index: 7604747 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3590. Min Range: -5.3590
Max Act: 5.0465. Min Act: -0.1700
Data Index: 7500096 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3590. Min Range: -5.3590
Max Act: 5.0465. Min Act: -0.1700
Data Index: 5790198 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3590. Min Range: -5.3590
Max Act: 5.0465. Min Act: -0.1700
Data Index: 5052805 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3590. Min Range: -5.3590
Max Act: 5.0153. Min Act: -0.1700
Data Index: 1787942 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3590. Min Range: -5.3590
Max Act: 5.0153. Min Act: -0.1700
Data Index: 5323269 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3590. Min Range: -5.3590
Max Act: 5.0153. Min Act: -0.1700
Data Index: 4117649 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3590. Min Range: -5.3590
Max Act: 5.0153. Min Act: -0.1700
Data Index: 6072545 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3590. Min Range: -5.3590
Max Act: 4.9840. Min Act: -0.1700
Data Index: 645453 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3590. Min Range: -5.3590
Max Act: 4.9840. Min Act: -0.1700
Data Index: 3217183 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19