Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 504 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7071. Min Range: -7.7071
Max Act: 7.7071. Min Act: -0.1700
Data Index: 8708178 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7071. Min Range: -7.7071
Max Act: 7.3008. Min Act: -0.1700
Data Index: 2066179 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7071. Min Range: -7.7071
Max Act: 7.2696. Min Act: -0.1700
Data Index: 6239570 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7071. Min Range: -7.7071
Max Act: 7.1758. Min Act: -0.1700
Data Index: 8478144 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7071. Min Range: -7.7071
Max Act: 7.1446. Min Act: -0.1700
Data Index: 675468 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7071. Min Range: -7.7071
Max Act: 7.1133. Min Act: -0.1700
Data Index: 1225591 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7071. Min Range: -7.7071
Max Act: 7.1133. Min Act: -0.1700
Data Index: 3099483 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7071. Min Range: -7.7071
Max Act: 7.1446. Min Act: -0.1700
Data Index: 4606884 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7071. Min Range: -7.7071
Max Act: 7.1133. Min Act: -0.1700
Data Index: 7781847 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7071. Min Range: -7.7071
Max Act: 7.0821. Min Act: -0.1700
Data Index: 3101023 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7071. Min Range: -7.7071
Max Act: 7.0821. Min Act: -0.1700
Data Index: 6976468 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7071. Min Range: -7.7071
Max Act: 7.0508. Min Act: -0.1700
Data Index: 2975922 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7071. Min Range: -7.7071
Max Act: 7.0196. Min Act: -0.1700
Data Index: 777571 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7071. Min Range: -7.7071
Max Act: 6.9883. Min Act: -0.1700
Data Index: 846685 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7071. Min Range: -7.7071
Max Act: 6.9571. Min Act: -0.1700
Data Index: 2186119 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7071. Min Range: -7.7071
Max Act: 6.9571. Min Act: -0.1700
Data Index: 5159640 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7071. Min Range: -7.7071
Max Act: 6.9571. Min Act: -0.1700
Data Index: 4406348 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7071. Min Range: -7.7071
Max Act: 6.9258. Min Act: -0.1700
Data Index: 3345144 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7071. Min Range: -7.7071
Max Act: 6.8633. Min Act: -0.1700
Data Index: 5229780 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7071. Min Range: -7.7071
Max Act: 6.8946. Min Act: -0.1700
Data Index: 4637940 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19