Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5734 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2831. Min Range: -6.2831
Max Act: 6.2831. Min Act: -0.1700
Data Index: 2300328 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2831. Min Range: -6.2831
Max Act: 6.1581. Min Act: -0.1700
Data Index: 478767 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2831. Min Range: -6.2831
Max Act: 6.1269. Min Act: -0.1700
Data Index: 1188164 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2831. Min Range: -6.2831
Max Act: 6.0331. Min Act: -0.1700
Data Index: 8316680 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2831. Min Range: -6.2831
Max Act: 6.0019. Min Act: -0.1700
Data Index: 6205662 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2831. Min Range: -6.2831
Max Act: 5.9394. Min Act: -0.1700
Data Index: 7473491 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2831. Min Range: -6.2831
Max Act: 5.8144. Min Act: -0.1700
Data Index: 8190013 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2831. Min Range: -6.2831
Max Act: 5.8144. Min Act: -0.1700
Data Index: 1090896 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2831. Min Range: -6.2831
Max Act: 5.8144. Min Act: -0.1700
Data Index: 5784902 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2831. Min Range: -6.2831
Max Act: 5.7831. Min Act: -0.1700
Data Index: 1220020 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2831. Min Range: -6.2831
Max Act: 5.7831. Min Act: -0.1700
Data Index: 7335609 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2831. Min Range: -6.2831
Max Act: 5.7831. Min Act: -0.1700
Data Index: 2120788 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2831. Min Range: -6.2831
Max Act: 5.7519. Min Act: -0.1700
Data Index: 4150648 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2831. Min Range: -6.2831
Max Act: 5.7519. Min Act: -0.1700
Data Index: 1419207 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2831. Min Range: -6.2831
Max Act: 5.7206. Min Act: -0.1700
Data Index: 6117935 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2831. Min Range: -6.2831
Max Act: 5.6894. Min Act: -0.1700
Data Index: 2977073 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2831. Min Range: -6.2831
Max Act: 5.7206. Min Act: -0.1700
Data Index: 1345628 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2831. Min Range: -6.2831
Max Act: 5.6894. Min Act: -0.1700
Data Index: 2462057 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2831. Min Range: -6.2831
Max Act: 5.6894. Min Act: -0.1700
Data Index: 4791197 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2831. Min Range: -6.2831
Max Act: 5.7206. Min Act: -0.1700
Data Index: 257427 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19