Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1366 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7844. Min Range: -2.7844
Max Act: 2.7844. Min Act: -0.1700
Data Index: 4564373 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7844. Min Range: -2.7844
Max Act: 2.7525. Min Act: -0.1700
Data Index: 7479715 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7844. Min Range: -2.7844
Max Act: 2.7366. Min Act: -0.1700
Data Index: 3927377 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7844. Min Range: -2.7844
Max Act: 2.7366. Min Act: -0.1700
Data Index: 3096252 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7844. Min Range: -2.7844
Max Act: 2.6405. Min Act: -0.1700
Data Index: 6806486 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7844. Min Range: -2.7844
Max Act: 2.6565. Min Act: -0.1700
Data Index: 3180826 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7844. Min Range: -2.7844
Max Act: 2.6565. Min Act: -0.1700
Data Index: 2898273 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7844. Min Range: -2.7844
Max Act: 2.6405. Min Act: -0.1700
Data Index: 3385473 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7844. Min Range: -2.7844
Max Act: 2.6405. Min Act: -0.1700
Data Index: 2012962 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7844. Min Range: -2.7844
Max Act: 2.6244. Min Act: -0.1700
Data Index: 6008461 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7844. Min Range: -2.7844
Max Act: 2.6244. Min Act: -0.1700
Data Index: 481187 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7844. Min Range: -2.7844
Max Act: 2.6083. Min Act: -0.1700
Data Index: 4504238 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7844. Min Range: -2.7844
Max Act: 2.6083. Min Act: -0.1700
Data Index: 348646 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7844. Min Range: -2.7844
Max Act: 2.6244. Min Act: -0.1700
Data Index: 72392 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7844. Min Range: -2.7844
Max Act: 2.6244. Min Act: -0.1700
Data Index: 7379302 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7844. Min Range: -2.7844
Max Act: 2.6083. Min Act: -0.1700
Data Index: 5345203 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7844. Min Range: -2.7844
Max Act: 2.6083. Min Act: -0.1700
Data Index: 3743164 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7844. Min Range: -2.7844
Max Act: 2.6244. Min Act: -0.1700
Data Index: 6316891 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7844. Min Range: -2.7844
Max Act: 2.6083. Min Act: -0.1700
Data Index: 4166596 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7844. Min Range: -2.7844
Max Act: 2.5922. Min Act: -0.1700
Data Index: 6059629 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19