Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1791 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7563. Min Range: -8.7563
Max Act: 8.7563. Min Act: -0.1700
Data Index: 2728903 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7563. Min Range: -8.7563
Max Act: 8.5063. Min Act: -0.1700
Data Index: 1686118 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7563. Min Range: -8.7563
Max Act: 8.2563. Min Act: -0.1700
Data Index: 7057557 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7563. Min Range: -8.7563
Max Act: 8.2563. Min Act: -0.1700
Data Index: 404862 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7563. Min Range: -8.7563
Max Act: 8.2563. Min Act: -0.1700
Data Index: 4587741 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7563. Min Range: -8.7563
Max Act: 8.1938. Min Act: -0.1700
Data Index: 6483505 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7563. Min Range: -8.7563
Max Act: 8.1313. Min Act: -0.1700
Data Index: 8037652 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7563. Min Range: -8.7563
Max Act: 8.1313. Min Act: -0.1700
Data Index: 8672544 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7563. Min Range: -8.7563
Max Act: 8.1313. Min Act: -0.1700
Data Index: 7796803 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7563. Min Range: -8.7563
Max Act: 8.1313. Min Act: -0.1700
Data Index: 1293891 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7563. Min Range: -8.7563
Max Act: 8.0688. Min Act: -0.1700
Data Index: 5500261 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7563. Min Range: -8.7563
Max Act: 8.1313. Min Act: -0.1700
Data Index: 1511919 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7563. Min Range: -8.7563
Max Act: 8.1313. Min Act: -0.1700
Data Index: 1560909 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7563. Min Range: -8.7563
Max Act: 8.0688. Min Act: -0.1700
Data Index: 2198373 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7563. Min Range: -8.7563
Max Act: 8.0063. Min Act: -0.1700
Data Index: 5458565 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7563. Min Range: -8.7563
Max Act: 8.0063. Min Act: -0.1700
Data Index: 3207750 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7563. Min Range: -8.7563
Max Act: 8.0063. Min Act: -0.1700
Data Index: 4656740 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7563. Min Range: -8.7563
Max Act: 8.0063. Min Act: -0.1700
Data Index: 3699799 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7563. Min Range: -8.7563
Max Act: 8.0063. Min Act: -0.1700
Data Index: 4538638 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7563. Min Range: -8.7563
Max Act: 8.0063. Min Act: -0.1700
Data Index: 5382880 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19