Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5347 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6298. Min Range: -5.6298
Max Act: 5.6298. Min Act: -0.1700
Data Index: 2454894 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6298. Min Range: -5.6298
Max Act: 5.3798. Min Act: -0.1700
Data Index: 2454893 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6298. Min Range: -5.6298
Max Act: 5.3486. Min Act: -0.1700
Data Index: 3998013 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6298. Min Range: -5.6298
Max Act: 5.0986. Min Act: -0.1700
Data Index: 4189262 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6298. Min Range: -5.6298
Max Act: 5.0361. Min Act: -0.1700
Data Index: 1928570 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6298. Min Range: -5.6298
Max Act: 4.9111. Min Act: -0.1700
Data Index: 707100 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6298. Min Range: -5.6298
Max Act: 4.9111. Min Act: -0.1700
Data Index: 5314597 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6298. Min Range: -5.6298
Max Act: 4.8798. Min Act: -0.1700
Data Index: 3424408 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6298. Min Range: -5.6298
Max Act: 4.7861. Min Act: -0.1700
Data Index: 7590515 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6298. Min Range: -5.6298
Max Act: 4.7861. Min Act: -0.1700
Data Index: 4843529 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6298. Min Range: -5.6298
Max Act: 4.7861. Min Act: -0.1700
Data Index: 2285002 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6298. Min Range: -5.6298
Max Act: 4.7861. Min Act: -0.1700
Data Index: 6144556 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6298. Min Range: -5.6298
Max Act: 4.6923. Min Act: -0.1700
Data Index: 6460113 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6298. Min Range: -5.6298
Max Act: 4.7236. Min Act: -0.1700
Data Index: 1958644 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6298. Min Range: -5.6298
Max Act: 4.6923. Min Act: -0.1700
Data Index: 4524457 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6298. Min Range: -5.6298
Max Act: 4.6923. Min Act: -0.1700
Data Index: 4545161 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6298. Min Range: -5.6298
Max Act: 4.6923. Min Act: -0.1700
Data Index: 3319699 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6298. Min Range: -5.6298
Max Act: 4.6923. Min Act: -0.1700
Data Index: 5819312 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6298. Min Range: -5.6298
Max Act: 4.6298. Min Act: -0.1700
Data Index: 3376160 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6298. Min Range: -5.6298
Max Act: 4.6611. Min Act: -0.1700
Data Index: 578898 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19