Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3239 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5840. Min Range: -9.5840
Max Act: 9.5840. Min Act: -0.1700
Data Index: 614089 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5840. Min Range: -9.5840
Max Act: 9.5215. Min Act: -0.1700
Data Index: 8035668 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5840. Min Range: -9.5840
Max Act: 9.2715. Min Act: -0.1700
Data Index: 8776423 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5840. Min Range: -9.5840
Max Act: 9.2715. Min Act: -0.1700
Data Index: 6792434 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5840. Min Range: -9.5840
Max Act: 9.1465. Min Act: -0.1700
Data Index: 2822883 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5840. Min Range: -9.5840
Max Act: 9.0840. Min Act: -0.1700
Data Index: 8756822 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5840. Min Range: -9.5840
Max Act: 9.0840. Min Act: -0.1700
Data Index: 3191577 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5840. Min Range: -9.5840
Max Act: 8.8965. Min Act: -0.1700
Data Index: 3120243 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5840. Min Range: -9.5840
Max Act: 8.8340. Min Act: -0.1700
Data Index: 5570301 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5840. Min Range: -9.5840
Max Act: 8.8340. Min Act: -0.1700
Data Index: 1939030 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5840. Min Range: -9.5840
Max Act: 8.7715. Min Act: -0.1700
Data Index: 2876544 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5840. Min Range: -9.5840
Max Act: 8.7715. Min Act: -0.1700
Data Index: 977506 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5840. Min Range: -9.5840
Max Act: 8.7090. Min Act: -0.1700
Data Index: 2760879 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5840. Min Range: -9.5840
Max Act: 8.7715. Min Act: -0.1700
Data Index: 721395 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5840. Min Range: -9.5840
Max Act: 8.7090. Min Act: -0.1700
Data Index: 7163201 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5840. Min Range: -9.5840
Max Act: 8.7090. Min Act: -0.1700
Data Index: 889643 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5840. Min Range: -9.5840
Max Act: 8.7090. Min Act: -0.1700
Data Index: 8788210 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5840. Min Range: -9.5840
Max Act: 8.6465. Min Act: -0.1700
Data Index: 3355217 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5840. Min Range: -9.5840
Max Act: 8.6465. Min Act: -0.1700
Data Index: 69355 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5840. Min Range: -9.5840
Max Act: 8.6465. Min Act: -0.1700
Data Index: 4646009 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #19