Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3799 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7101. Min Range: -8.7101
Max Act: 8.7101. Min Act: -0.1700
Data Index: 8712583 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7101. Min Range: -8.7101
Max Act: 8.3351. Min Act: -0.1700
Data Index: 3573167 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7101. Min Range: -8.7101
Max Act: 8.1476. Min Act: -0.1700
Data Index: 8601968 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7101. Min Range: -8.7101
Max Act: 8.0851. Min Act: -0.1700
Data Index: 5820701 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7101. Min Range: -8.7101
Max Act: 8.0851. Min Act: -0.1700
Data Index: 7096130 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7101. Min Range: -8.7101
Max Act: 7.9601. Min Act: -0.1700
Data Index: 2488114 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7101. Min Range: -8.7101
Max Act: 7.9601. Min Act: -0.1700
Data Index: 4860673 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7101. Min Range: -8.7101
Max Act: 7.8976. Min Act: -0.1700
Data Index: 3780270 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7101. Min Range: -8.7101
Max Act: 7.8351. Min Act: -0.1700
Data Index: 1473223 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7101. Min Range: -8.7101
Max Act: 7.8351. Min Act: -0.1700
Data Index: 5845109 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7101. Min Range: -8.7101
Max Act: 7.7726. Min Act: -0.1700
Data Index: 7616230 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7101. Min Range: -8.7101
Max Act: 7.7101. Min Act: -0.1700
Data Index: 5103519 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7101. Min Range: -8.7101
Max Act: 7.6476. Min Act: -0.1700
Data Index: 601549 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7101. Min Range: -8.7101
Max Act: 7.6476. Min Act: -0.1700
Data Index: 4413380 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7101. Min Range: -8.7101
Max Act: 7.7101. Min Act: -0.1700
Data Index: 8181960 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7101. Min Range: -8.7101
Max Act: 7.5539. Min Act: -0.1700
Data Index: 2107214 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7101. Min Range: -8.7101
Max Act: 7.5851. Min Act: -0.1700
Data Index: 6499249 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7101. Min Range: -8.7101
Max Act: 7.5851. Min Act: -0.1700
Data Index: 4933134 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7101. Min Range: -8.7101
Max Act: 7.5851. Min Act: -0.1700
Data Index: 7849643 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7101. Min Range: -8.7101
Max Act: 7.5539. Min Act: -0.1700
Data Index: 7134313 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19