Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2918 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1718. Min Range: -8.1718
Max Act: 8.1718. Min Act: -0.1700
Data Index: 3891073 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1718. Min Range: -8.1718
Max Act: 7.9218. Min Act: -0.1700
Data Index: 725086 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1718. Min Range: -8.1718
Max Act: 7.9843. Min Act: -0.1700
Data Index: 8411198 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1718. Min Range: -8.1718
Max Act: 7.9843. Min Act: -0.1700
Data Index: 5274465 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1718. Min Range: -8.1718
Max Act: 7.7968. Min Act: -0.1700
Data Index: 4939707 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1718. Min Range: -8.1718
Max Act: 7.8593. Min Act: -0.1700
Data Index: 1882414 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1718. Min Range: -8.1718
Max Act: 7.8593. Min Act: -0.1700
Data Index: 433800 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1718. Min Range: -8.1718
Max Act: 7.7343. Min Act: -0.1700
Data Index: 6396943 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1718. Min Range: -8.1718
Max Act: 7.7968. Min Act: -0.1700
Data Index: 8765997 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1718. Min Range: -8.1718
Max Act: 7.7343. Min Act: -0.1700
Data Index: 5492580 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1718. Min Range: -8.1718
Max Act: 7.7031. Min Act: -0.1700
Data Index: 2062594 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1718. Min Range: -8.1718
Max Act: 7.6406. Min Act: -0.1700
Data Index: 6290504 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1718. Min Range: -8.1718
Max Act: 7.6406. Min Act: -0.1700
Data Index: 1395130 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1718. Min Range: -8.1718
Max Act: 7.6093. Min Act: -0.1700
Data Index: 1337518 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1718. Min Range: -8.1718
Max Act: 7.5781. Min Act: -0.1700
Data Index: 7468813 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1718. Min Range: -8.1718
Max Act: 7.5781. Min Act: -0.1700
Data Index: 7626244 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1718. Min Range: -8.1718
Max Act: 7.5781. Min Act: -0.1700
Data Index: 4056149 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1718. Min Range: -8.1718
Max Act: 7.6093. Min Act: -0.1700
Data Index: 2603534 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1718. Min Range: -8.1718
Max Act: 7.5468. Min Act: -0.1700
Data Index: 4106371 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1718. Min Range: -8.1718
Max Act: 7.5468. Min Act: -0.1700
Data Index: 3825363 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19