Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4898 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0984. Min Range: -7.0984
Max Act: 7.0984. Min Act: -0.1700
Data Index: 4571875 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0984. Min Range: -7.0984
Max Act: 6.7546. Min Act: -0.1700
Data Index: 6006642 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0984. Min Range: -7.0984
Max Act: 6.7859. Min Act: -0.1700
Data Index: 1537781 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0984. Min Range: -7.0984
Max Act: 6.7234. Min Act: -0.1700
Data Index: 1391287 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0984. Min Range: -7.0984
Max Act: 6.6921. Min Act: -0.1700
Data Index: 7651154 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0984. Min Range: -7.0984
Max Act: 6.6921. Min Act: -0.1700
Data Index: 2052548 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0984. Min Range: -7.0984
Max Act: 6.6296. Min Act: -0.1700
Data Index: 2036264 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0984. Min Range: -7.0984
Max Act: 6.6921. Min Act: -0.1700
Data Index: 5322704 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0984. Min Range: -7.0984
Max Act: 6.5984. Min Act: -0.1700
Data Index: 385454 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0984. Min Range: -7.0984
Max Act: 6.6296. Min Act: -0.1700
Data Index: 1750040 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0984. Min Range: -7.0984
Max Act: 6.6296. Min Act: -0.1700
Data Index: 3331467 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0984. Min Range: -7.0984
Max Act: 6.5984. Min Act: -0.1700
Data Index: 452351 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0984. Min Range: -7.0984
Max Act: 6.5671. Min Act: -0.1700
Data Index: 1946498 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0984. Min Range: -7.0984
Max Act: 6.5046. Min Act: -0.1700
Data Index: 8225777 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0984. Min Range: -7.0984
Max Act: 6.5046. Min Act: -0.1700
Data Index: 1714288 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0984. Min Range: -7.0984
Max Act: 6.4734. Min Act: -0.1700
Data Index: 1731059 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0984. Min Range: -7.0984
Max Act: 6.4734. Min Act: -0.1700
Data Index: 4221565 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0984. Min Range: -7.0984
Max Act: 6.4109. Min Act: -0.1700
Data Index: 5237052 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0984. Min Range: -7.0984
Max Act: 6.4109. Min Act: -0.1700
Data Index: 5961468 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0984. Min Range: -7.0984
Max Act: 6.4109. Min Act: -0.1700
Data Index: 320091 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #19