Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5596 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2884. Min Range: -7.2884
Max Act: 7.2884. Min Act: -0.1700
Data Index: 5295211 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2884. Min Range: -7.2884
Max Act: 7.2572. Min Act: -0.1700
Data Index: 782956 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2884. Min Range: -7.2884
Max Act: 7.1634. Min Act: -0.1700
Data Index: 7915966 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2884. Min Range: -7.2884
Max Act: 7.0697. Min Act: -0.1700
Data Index: 1560749 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2884. Min Range: -7.2884
Max Act: 6.9759. Min Act: -0.1700
Data Index: 3471045 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2884. Min Range: -7.2884
Max Act: 6.9447. Min Act: -0.1700
Data Index: 6494067 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2884. Min Range: -7.2884
Max Act: 6.8822. Min Act: -0.1700
Data Index: 3694620 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2884. Min Range: -7.2884
Max Act: 6.8822. Min Act: -0.1700
Data Index: 8129909 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2884. Min Range: -7.2884
Max Act: 6.7884. Min Act: -0.1700
Data Index: 5295217 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2884. Min Range: -7.2884
Max Act: 6.8509. Min Act: -0.1700
Data Index: 900147 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2884. Min Range: -7.2884
Max Act: 6.7572. Min Act: -0.1700
Data Index: 8389965 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2884. Min Range: -7.2884
Max Act: 6.7884. Min Act: -0.1700
Data Index: 533923 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2884. Min Range: -7.2884
Max Act: 6.7884. Min Act: -0.1700
Data Index: 4017788 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2884. Min Range: -7.2884
Max Act: 6.7572. Min Act: -0.1700
Data Index: 8075288 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2884. Min Range: -7.2884
Max Act: 6.7259. Min Act: -0.1700
Data Index: 7224805 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2884. Min Range: -7.2884
Max Act: 6.7572. Min Act: -0.1700
Data Index: 1452027 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2884. Min Range: -7.2884
Max Act: 6.7259. Min Act: -0.1700
Data Index: 1996089 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2884. Min Range: -7.2884
Max Act: 6.6947. Min Act: -0.1700
Data Index: 1045020 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2884. Min Range: -7.2884
Max Act: 6.7572. Min Act: -0.1700
Data Index: 2680604 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2884. Min Range: -7.2884
Max Act: 6.6947. Min Act: -0.1700
Data Index: 7290709 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19