Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1802 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6828. Min Range: -6.6828
Max Act: 6.6828. Min Act: -0.1700
Data Index: 1053626 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6828. Min Range: -6.6828
Max Act: 6.4328. Min Act: -0.1700
Data Index: 7979137 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6828. Min Range: -6.6828
Max Act: 6.3391. Min Act: -0.1700
Data Index: 4220818 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6828. Min Range: -6.6828
Max Act: 6.3391. Min Act: -0.1700
Data Index: 8596749 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6828. Min Range: -6.6828
Max Act: 6.2766. Min Act: -0.1700
Data Index: 2760647 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6828. Min Range: -6.6828
Max Act: 6.2766. Min Act: -0.1700
Data Index: 1340014 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6828. Min Range: -6.6828
Max Act: 6.2766. Min Act: -0.1700
Data Index: 6028873 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6828. Min Range: -6.6828
Max Act: 6.2141. Min Act: -0.1700
Data Index: 1718023 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6828. Min Range: -6.6828
Max Act: 6.2453. Min Act: -0.1700
Data Index: 707284 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6828. Min Range: -6.6828
Max Act: 6.1828. Min Act: -0.1700
Data Index: 3162926 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6828. Min Range: -6.6828
Max Act: 6.2141. Min Act: -0.1700
Data Index: 3502781 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6828. Min Range: -6.6828
Max Act: 6.1828. Min Act: -0.1700
Data Index: 8383514 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6828. Min Range: -6.6828
Max Act: 6.1828. Min Act: -0.1700
Data Index: 5803173 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6828. Min Range: -6.6828
Max Act: 6.1516. Min Act: -0.1700
Data Index: 4636365 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6828. Min Range: -6.6828
Max Act: 6.1516. Min Act: -0.1700
Data Index: 3056715 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6828. Min Range: -6.6828
Max Act: 6.1516. Min Act: -0.1700
Data Index: 577004 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6828. Min Range: -6.6828
Max Act: 6.1203. Min Act: -0.1700
Data Index: 4759408 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6828. Min Range: -6.6828
Max Act: 6.1203. Min Act: -0.1700
Data Index: 5543923 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6828. Min Range: -6.6828
Max Act: 6.1203. Min Act: -0.1700
Data Index: 6670698 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6828. Min Range: -6.6828
Max Act: 6.1203. Min Act: -0.1700
Data Index: 7114511 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #19