Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2756 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1845. Min Range: -9.1845
Max Act: 9.1845. Min Act: -0.1700
Data Index: 2890386 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1845. Min Range: -9.1845
Max Act: 9.1220. Min Act: -0.1700
Data Index: 2232969 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1845. Min Range: -9.1845
Max Act: 9.0595. Min Act: -0.1700
Data Index: 382999 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1845. Min Range: -9.1845
Max Act: 8.9970. Min Act: -0.1700
Data Index: 6760068 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1845. Min Range: -9.1845
Max Act: 8.9970. Min Act: -0.1700
Data Index: 955315 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1845. Min Range: -9.1845
Max Act: 8.9970. Min Act: -0.1700
Data Index: 2827664 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1845. Min Range: -9.1845
Max Act: 8.9345. Min Act: -0.1700
Data Index: 412215 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1845. Min Range: -9.1845
Max Act: 8.9345. Min Act: -0.1700
Data Index: 3721394 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1845. Min Range: -9.1845
Max Act: 8.8095. Min Act: -0.1700
Data Index: 6530705 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1845. Min Range: -9.1845
Max Act: 8.8720. Min Act: -0.1700
Data Index: 5295564 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1845. Min Range: -9.1845
Max Act: 8.8720. Min Act: -0.1700
Data Index: 2317005 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1845. Min Range: -9.1845
Max Act: 8.8095. Min Act: -0.1700
Data Index: 8611829 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1845. Min Range: -9.1845
Max Act: 8.8095. Min Act: -0.1700
Data Index: 7561841 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1845. Min Range: -9.1845
Max Act: 8.8095. Min Act: -0.1700
Data Index: 5268419 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1845. Min Range: -9.1845
Max Act: 8.8095. Min Act: -0.1700
Data Index: 2639136 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1845. Min Range: -9.1845
Max Act: 8.8095. Min Act: -0.1700
Data Index: 2010001 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1845. Min Range: -9.1845
Max Act: 8.8095. Min Act: -0.1700
Data Index: 5542078 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1845. Min Range: -9.1845
Max Act: 8.8095. Min Act: -0.1700
Data Index: 4933891 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1845. Min Range: -9.1845
Max Act: 8.6845. Min Act: -0.1700
Data Index: 605812 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1845. Min Range: -9.1845
Max Act: 8.7470. Min Act: -0.1700
Data Index: 5436747 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19