Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1279 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1370. Min Range: -7.1370
Max Act: 7.1370. Min Act: -0.1700
Data Index: 7365102 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1370. Min Range: -7.1370
Max Act: 7.0120. Min Act: -0.1700
Data Index: 7542906 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1370. Min Range: -7.1370
Max Act: 6.9183. Min Act: -0.1700
Data Index: 2181610 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1370. Min Range: -7.1370
Max Act: 6.9183. Min Act: -0.1700
Data Index: 753712 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1370. Min Range: -7.1370
Max Act: 6.8558. Min Act: -0.1700
Data Index: 4224885 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1370. Min Range: -7.1370
Max Act: 6.8558. Min Act: -0.1700
Data Index: 7707467 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1370. Min Range: -7.1370
Max Act: 6.8245. Min Act: -0.1700
Data Index: 4263971 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1370. Min Range: -7.1370
Max Act: 6.8245. Min Act: -0.1700
Data Index: 5256276 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1370. Min Range: -7.1370
Max Act: 6.7620. Min Act: -0.1700
Data Index: 325985 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1370. Min Range: -7.1370
Max Act: 6.7620. Min Act: -0.1700
Data Index: 7720527 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1370. Min Range: -7.1370
Max Act: 6.6995. Min Act: -0.1700
Data Index: 451395 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1370. Min Range: -7.1370
Max Act: 6.6683. Min Act: -0.1700
Data Index: 7034021 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1370. Min Range: -7.1370
Max Act: 6.6683. Min Act: -0.1700
Data Index: 3315889 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1370. Min Range: -7.1370
Max Act: 6.6683. Min Act: -0.1700
Data Index: 7630436 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1370. Min Range: -7.1370
Max Act: 6.6683. Min Act: -0.1700
Data Index: 6013687 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1370. Min Range: -7.1370
Max Act: 6.6683. Min Act: -0.1700
Data Index: 5533456 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1370. Min Range: -7.1370
Max Act: 6.6683. Min Act: -0.1700
Data Index: 1549864 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1370. Min Range: -7.1370
Max Act: 6.6058. Min Act: -0.1700
Data Index: 822840 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1370. Min Range: -7.1370
Max Act: 6.6058. Min Act: -0.1700
Data Index: 5131764 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1370. Min Range: -7.1370
Max Act: 6.5745. Min Act: -0.1700
Data Index: 6145557 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19