Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3903 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.9072. Min Act: -0.1700
Data Index: 5759161 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.7822. Min Act: -0.1700
Data Index: 642969 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.6260. Min Act: -0.1700
Data Index: 1538406 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.5635. Min Act: -0.1700
Data Index: 7426121 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.5322. Min Act: -0.1700
Data Index: 8734993 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.5010. Min Act: -0.1700
Data Index: 5207009 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.3760. Min Act: -0.1700
Data Index: 1153107 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.3760. Min Act: -0.1700
Data Index: 6434491 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.3760. Min Act: -0.1700
Data Index: 7459001 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.3447. Min Act: -0.1700
Data Index: 2743900 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.3447. Min Act: -0.1700
Data Index: 2615929 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.3135. Min Act: -0.1700
Data Index: 7426118 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.2822. Min Act: -0.1700
Data Index: 1762299 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.2822. Min Act: -0.1700
Data Index: 6949330 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.2510. Min Act: -0.1700
Data Index: 7869837 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.2510. Min Act: -0.1700
Data Index: 2825456 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.2197. Min Act: -0.1700
Data Index: 1817866 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.2197. Min Act: -0.1700
Data Index: 8623687 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.1260. Min Act: -0.1700
Data Index: 2095224 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.1572. Min Act: -0.1700
Data Index: 523839 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19