Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6021 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5508. Min Range: -6.5508
Max Act: 6.5508. Min Act: -0.1700
Data Index: 4527255 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5508. Min Range: -6.5508
Max Act: 6.3321. Min Act: -0.1700
Data Index: 7016903 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5508. Min Range: -6.5508
Max Act: 6.3008. Min Act: -0.1700
Data Index: 4518164 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5508. Min Range: -6.5508
Max Act: 6.2696. Min Act: -0.1700
Data Index: 5893665 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5508. Min Range: -6.5508
Max Act: 6.2696. Min Act: -0.1700
Data Index: 5923310 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5508. Min Range: -6.5508
Max Act: 6.2696. Min Act: -0.1700
Data Index: 7974851 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5508. Min Range: -6.5508
Max Act: 6.2383. Min Act: -0.1700
Data Index: 6467054 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5508. Min Range: -6.5508
Max Act: 6.2071. Min Act: -0.1700
Data Index: 437610 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5508. Min Range: -6.5508
Max Act: 6.2071. Min Act: -0.1700
Data Index: 6536834 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5508. Min Range: -6.5508
Max Act: 6.1758. Min Act: -0.1700
Data Index: 1284794 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5508. Min Range: -6.5508
Max Act: 6.1758. Min Act: -0.1700
Data Index: 2650600 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5508. Min Range: -6.5508
Max Act: 6.1758. Min Act: -0.1700
Data Index: 6021345 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5508. Min Range: -6.5508
Max Act: 6.1758. Min Act: -0.1700
Data Index: 4793975 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5508. Min Range: -6.5508
Max Act: 6.1446. Min Act: -0.1700
Data Index: 2442867 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5508. Min Range: -6.5508
Max Act: 6.1446. Min Act: -0.1700
Data Index: 6072654 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5508. Min Range: -6.5508
Max Act: 6.1446. Min Act: -0.1700
Data Index: 6147779 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5508. Min Range: -6.5508
Max Act: 6.1446. Min Act: -0.1700
Data Index: 5610978 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5508. Min Range: -6.5508
Max Act: 6.1446. Min Act: -0.1700
Data Index: 739946 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5508. Min Range: -6.5508
Max Act: 6.0821. Min Act: -0.1700
Data Index: 3927831 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5508. Min Range: -6.5508
Max Act: 6.1133. Min Act: -0.1700
Data Index: 552714 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19