Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3407 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2791. Min Range: -5.2791
Max Act: 5.2791. Min Act: -0.1700
Data Index: 2093777 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2791. Min Range: -5.2791
Max Act: 5.2791. Min Act: -0.1700
Data Index: 4886688 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2791. Min Range: -5.2791
Max Act: 5.2791. Min Act: -0.1700
Data Index: 1573256 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2791. Min Range: -5.2791
Max Act: 5.2791. Min Act: -0.1699
Data Index: 5065760 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2791. Min Range: -5.2791
Max Act: 5.2791. Min Act: -0.1700
Data Index: 8786067 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2791. Min Range: -5.2791
Max Act: 5.2791. Min Act: -0.1700
Data Index: 1263026 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2791. Min Range: -5.2791
Max Act: 5.2478. Min Act: -0.1700
Data Index: 4918090 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2791. Min Range: -5.2791
Max Act: 5.2478. Min Act: -0.1700
Data Index: 8732890 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2791. Min Range: -5.2791
Max Act: 5.2791. Min Act: -0.1700
Data Index: 7285253 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2791. Min Range: -5.2791
Max Act: 5.2478. Min Act: -0.1700
Data Index: 6021919 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2791. Min Range: -5.2791
Max Act: 5.2166. Min Act: -0.1700
Data Index: 569936 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2791. Min Range: -5.2791
Max Act: 5.2166. Min Act: -0.1700
Data Index: 7583223 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2791. Min Range: -5.2791
Max Act: 5.2166. Min Act: -0.1700
Data Index: 2978914 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2791. Min Range: -5.2791
Max Act: 5.1853. Min Act: -0.1700
Data Index: 219694 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2791. Min Range: -5.2791
Max Act: 5.1853. Min Act: -0.1700
Data Index: 7083419 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2791. Min Range: -5.2791
Max Act: 5.1853. Min Act: -0.1699
Data Index: 1331167 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2791. Min Range: -5.2791
Max Act: 5.1853. Min Act: -0.1700
Data Index: 3932444 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2791. Min Range: -5.2791
Max Act: 5.2166. Min Act: -0.1700
Data Index: 3528380 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2791. Min Range: -5.2791
Max Act: 5.1853. Min Act: -0.1700
Data Index: 3496859 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2791. Min Range: -5.2791
Max Act: 5.1853. Min Act: -0.1700
Data Index: 1890935 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19