Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5001 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0938. Min Range: -5.0938
Max Act: 5.0938. Min Act: -0.1700
Data Index: 7809054 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0938. Min Range: -5.0938
Max Act: 5.0938. Min Act: -0.1700
Data Index: 3354523 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0938. Min Range: -5.0938
Max Act: 5.0938. Min Act: -0.1700
Data Index: 6430937 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0938. Min Range: -5.0938
Max Act: 5.0625. Min Act: -0.1700
Data Index: 4242502 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0938. Min Range: -5.0938
Max Act: 5.0000. Min Act: -0.1700
Data Index: 4074978 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0938. Min Range: -5.0938
Max Act: 4.9063. Min Act: -0.1700
Data Index: 473365 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0938. Min Range: -5.0938
Max Act: 4.8750. Min Act: -0.1700
Data Index: 2276712 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0938. Min Range: -5.0938
Max Act: 4.9063. Min Act: -0.1700
Data Index: 4160036 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0938. Min Range: -5.0938
Max Act: 4.9063. Min Act: -0.1700
Data Index: 6190119 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0938. Min Range: -5.0938
Max Act: 4.9063. Min Act: -0.1700
Data Index: 3765003 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0938. Min Range: -5.0938
Max Act: 4.8438. Min Act: -0.1700
Data Index: 7456930 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0938. Min Range: -5.0938
Max Act: 4.8438. Min Act: -0.1700
Data Index: 2622307 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0938. Min Range: -5.0938
Max Act: 4.8438. Min Act: -0.1700
Data Index: 55342 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0938. Min Range: -5.0938
Max Act: 4.8438. Min Act: -0.1700
Data Index: 4633152 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0938. Min Range: -5.0938
Max Act: 4.8125. Min Act: -0.1700
Data Index: 3628209 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0938. Min Range: -5.0938
Max Act: 4.7813. Min Act: -0.1700
Data Index: 8806863 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0938. Min Range: -5.0938
Max Act: 4.7813. Min Act: -0.1700
Data Index: 6605405 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0938. Min Range: -5.0938
Max Act: 4.7813. Min Act: -0.1700
Data Index: 4902201 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0938. Min Range: -5.0938
Max Act: 4.7813. Min Act: -0.1700
Data Index: 7843743 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0938. Min Range: -5.0938
Max Act: 4.7500. Min Act: -0.1700
Data Index: 1970472 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #19