Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4566 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5601. Min Range: -6.5601
Max Act: 6.5601. Min Act: -0.1700
Data Index: 4188101 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5601. Min Range: -6.5601
Max Act: 6.4664. Min Act: -0.1700
Data Index: 3525748 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5601. Min Range: -6.5601
Max Act: 6.4664. Min Act: -0.1700
Data Index: 573786 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5601. Min Range: -6.5601
Max Act: 6.3414. Min Act: -0.1700
Data Index: 3523697 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5601. Min Range: -6.5601
Max Act: 6.3101. Min Act: -0.1700
Data Index: 1916046 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5601. Min Range: -6.5601
Max Act: 6.3101. Min Act: -0.1700
Data Index: 8717883 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5601. Min Range: -6.5601
Max Act: 6.2789. Min Act: -0.1700
Data Index: 1997629 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5601. Min Range: -6.5601
Max Act: 6.2789. Min Act: -0.1700
Data Index: 8330745 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5601. Min Range: -6.5601
Max Act: 6.2789. Min Act: -0.1700
Data Index: 2321760 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5601. Min Range: -6.5601
Max Act: 6.2789. Min Act: -0.1700
Data Index: 6419902 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5601. Min Range: -6.5601
Max Act: 6.2789. Min Act: -0.1700
Data Index: 2515267 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5601. Min Range: -6.5601
Max Act: 6.2476. Min Act: -0.1700
Data Index: 5797907 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5601. Min Range: -6.5601
Max Act: 6.2789. Min Act: -0.1700
Data Index: 5902560 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5601. Min Range: -6.5601
Max Act: 6.2476. Min Act: -0.1700
Data Index: 4253302 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5601. Min Range: -6.5601
Max Act: 6.2476. Min Act: -0.1700
Data Index: 5393902 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5601. Min Range: -6.5601
Max Act: 6.2476. Min Act: -0.1700
Data Index: 8173764 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5601. Min Range: -6.5601
Max Act: 6.2476. Min Act: -0.1700
Data Index: 3623318 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5601. Min Range: -6.5601
Max Act: 6.2476. Min Act: -0.1700
Data Index: 6551375 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5601. Min Range: -6.5601
Max Act: 6.2164. Min Act: -0.1700
Data Index: 4365256 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5601. Min Range: -6.5601
Max Act: 6.2164. Min Act: -0.1700
Data Index: 2125873 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19