Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4633 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9120. Min Range: -10.9120
Max Act: 10.9120. Min Act: -0.1700
Data Index: 4994232 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9120. Min Range: -10.9120
Max Act: 10.7870. Min Act: -0.1700
Data Index: 1216621 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9120. Min Range: -10.9120
Max Act: 10.7870. Min Act: -0.1700
Data Index: 6813730 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9120. Min Range: -10.9120
Max Act: 10.7870. Min Act: -0.1700
Data Index: 2972376 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9120. Min Range: -10.9120
Max Act: 10.6620. Min Act: -0.1700
Data Index: 7930468 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9120. Min Range: -10.9120
Max Act: 10.7245. Min Act: -0.1700
Data Index: 4932478 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9120. Min Range: -10.9120
Max Act: 10.7245. Min Act: -0.1700
Data Index: 2792368 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9120. Min Range: -10.9120
Max Act: 10.7245. Min Act: -0.1700
Data Index: 4668027 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9120. Min Range: -10.9120
Max Act: 10.6620. Min Act: -0.1700
Data Index: 5676853 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9120. Min Range: -10.9120
Max Act: 10.6620. Min Act: -0.1700
Data Index: 1916789 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9120. Min Range: -10.9120
Max Act: 10.6620. Min Act: -0.1700
Data Index: 8432703 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9120. Min Range: -10.9120
Max Act: 10.6620. Min Act: -0.1700
Data Index: 264789 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9120. Min Range: -10.9120
Max Act: 10.6620. Min Act: -0.1700
Data Index: 1062898 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9120. Min Range: -10.9120
Max Act: 10.5995. Min Act: -0.1700
Data Index: 2217638 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9120. Min Range: -10.9120
Max Act: 10.5995. Min Act: -0.1700
Data Index: 4952488 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9120. Min Range: -10.9120
Max Act: 10.5995. Min Act: -0.1700
Data Index: 8178494 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9120. Min Range: -10.9120
Max Act: 10.5370. Min Act: -0.1700
Data Index: 5059410 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9120. Min Range: -10.9120
Max Act: 10.4745. Min Act: -0.1700
Data Index: 4244373 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9120. Min Range: -10.9120
Max Act: 10.5370. Min Act: -0.1693
Data Index: 688733 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9120. Min Range: -10.9120
Max Act: 10.5370. Min Act: -0.1700
Data Index: 5383768 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19