Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4019 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9124. Min Range: -7.9124
Max Act: 7.9124. Min Act: -0.1700
Data Index: 8296957 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9124. Min Range: -7.9124
Max Act: 7.6936. Min Act: -0.1700
Data Index: 4357448 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9124. Min Range: -7.9124
Max Act: 7.6311. Min Act: -0.1698
Data Index: 1500607 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9124. Min Range: -7.9124
Max Act: 7.5686. Min Act: -0.1700
Data Index: 6605805 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9124. Min Range: -7.9124
Max Act: 7.5374. Min Act: -0.1700
Data Index: 1245722 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9124. Min Range: -7.9124
Max Act: 7.5061. Min Act: -0.1700
Data Index: 7780289 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9124. Min Range: -7.9124
Max Act: 7.2249. Min Act: -0.1700
Data Index: 5593266 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9124. Min Range: -7.9124
Max Act: 7.2561. Min Act: -0.1700
Data Index: 155454 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9124. Min Range: -7.9124
Max Act: 7.2561. Min Act: -0.1700
Data Index: 349250 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9124. Min Range: -7.9124
Max Act: 7.2249. Min Act: -0.1700
Data Index: 7873595 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9124. Min Range: -7.9124
Max Act: 7.1936. Min Act: -0.1700
Data Index: 2906636 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9124. Min Range: -7.9124
Max Act: 7.2249. Min Act: -0.1700
Data Index: 1320996 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9124. Min Range: -7.9124
Max Act: 7.1936. Min Act: -0.1700
Data Index: 3712621 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9124. Min Range: -7.9124
Max Act: 7.1936. Min Act: -0.1700
Data Index: 4233307 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9124. Min Range: -7.9124
Max Act: 7.1936. Min Act: -0.1700
Data Index: 8386538 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9124. Min Range: -7.9124
Max Act: 7.1311. Min Act: -0.1700
Data Index: 2971006 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9124. Min Range: -7.9124
Max Act: 7.1311. Min Act: -0.1700
Data Index: 300841 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9124. Min Range: -7.9124
Max Act: 7.1624. Min Act: -0.1700
Data Index: 4682325 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9124. Min Range: -7.9124
Max Act: 7.1311. Min Act: -0.1700
Data Index: 824008 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9124. Min Range: -7.9124
Max Act: 7.1311. Min Act: -0.1700
Data Index: 3223537 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19