Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 540 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1384. Min Range: -8.1384
Max Act: 8.1384. Min Act: -0.1700
Data Index: 6024501 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1384. Min Range: -8.1384
Max Act: 8.0134. Min Act: -0.1700
Data Index: 7949342 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1384. Min Range: -8.1384
Max Act: 8.0134. Min Act: -0.1700
Data Index: 7683803 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1384. Min Range: -8.1384
Max Act: 8.0134. Min Act: -0.1700
Data Index: 8817628 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1384. Min Range: -8.1384
Max Act: 8.0134. Min Act: -0.1700
Data Index: 6711367 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1384. Min Range: -8.1384
Max Act: 8.0134. Min Act: -0.1700
Data Index: 6172215 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1384. Min Range: -8.1384
Max Act: 7.9509. Min Act: -0.1700
Data Index: 4811630 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1384. Min Range: -8.1384
Max Act: 7.8884. Min Act: -0.1700
Data Index: 6280851 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1384. Min Range: -8.1384
Max Act: 7.8259. Min Act: -0.1700
Data Index: 4811629 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1384. Min Range: -8.1384
Max Act: 7.8259. Min Act: -0.1700
Data Index: 7351667 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1384. Min Range: -8.1384
Max Act: 7.8259. Min Act: -0.1700
Data Index: 1702723 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1384. Min Range: -8.1384
Max Act: 7.8259. Min Act: -0.1700
Data Index: 93294 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1384. Min Range: -8.1384
Max Act: 7.7634. Min Act: -0.1700
Data Index: 8815118 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1384. Min Range: -8.1384
Max Act: 7.8259. Min Act: -0.1700
Data Index: 5618676 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1384. Min Range: -8.1384
Max Act: 7.7634. Min Act: -0.1700
Data Index: 516611 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1384. Min Range: -8.1384
Max Act: 7.7634. Min Act: -0.1700
Data Index: 8636206 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1384. Min Range: -8.1384
Max Act: 7.7009. Min Act: -0.1700
Data Index: 7635825 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1384. Min Range: -8.1384
Max Act: 7.7634. Min Act: -0.1700
Data Index: 3030815 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1384. Min Range: -8.1384
Max Act: 7.7009. Min Act: -0.1700
Data Index: 33266 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1384. Min Range: -8.1384
Max Act: 7.7009. Min Act: -0.1700
Data Index: 4915303 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19