Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 815 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2768. Min Range: -8.2768
Max Act: 8.2768. Min Act: -0.1700
Data Index: 2547351 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2768. Min Range: -8.2768
Max Act: 8.2143. Min Act: -0.1700
Data Index: 597411 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2768. Min Range: -8.2768
Max Act: 8.1518. Min Act: -0.1700
Data Index: 7969451 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2768. Min Range: -8.2768
Max Act: 8.1518. Min Act: -0.1700
Data Index: 781273 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2768. Min Range: -8.2768
Max Act: 7.9018. Min Act: -0.1700
Data Index: 5748911 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2768. Min Range: -8.2768
Max Act: 7.9018. Min Act: -0.1700
Data Index: 5187730 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2768. Min Range: -8.2768
Max Act: 7.8393. Min Act: -0.1700
Data Index: 246551 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2768. Min Range: -8.2768
Max Act: 7.7768. Min Act: -0.1700
Data Index: 8065650 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2768. Min Range: -8.2768
Max Act: 7.7768. Min Act: -0.1700
Data Index: 2784821 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2768. Min Range: -8.2768
Max Act: 7.7143. Min Act: -0.1700
Data Index: 3510853 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2768. Min Range: -8.2768
Max Act: 7.7768. Min Act: -0.1700
Data Index: 6922749 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2768. Min Range: -8.2768
Max Act: 7.7143. Min Act: -0.1700
Data Index: 3093404 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2768. Min Range: -8.2768
Max Act: 7.6518. Min Act: -0.1700
Data Index: 1564731 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2768. Min Range: -8.2768
Max Act: 7.6518. Min Act: -0.1700
Data Index: 161402 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2768. Min Range: -8.2768
Max Act: 7.6518. Min Act: -0.1700
Data Index: 6810331 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2768. Min Range: -8.2768
Max Act: 7.6518. Min Act: -0.1700
Data Index: 149815 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2768. Min Range: -8.2768
Max Act: 7.5268. Min Act: -0.1700
Data Index: 5473721 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2768. Min Range: -8.2768
Max Act: 7.5268. Min Act: -0.1700
Data Index: 1650688 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2768. Min Range: -8.2768
Max Act: 7.5268. Min Act: -0.1700
Data Index: 4730635 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2768. Min Range: -8.2768
Max Act: 7.5268. Min Act: -0.1700
Data Index: 5684611 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19