Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4274 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2462. Min Range: -7.2462
Max Act: 7.2462. Min Act: -0.1700
Data Index: 7753915 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2462. Min Range: -7.2462
Max Act: 7.1524. Min Act: -0.1700
Data Index: 3742488 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2462. Min Range: -7.2462
Max Act: 6.9962. Min Act: -0.1700
Data Index: 6252491 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2462. Min Range: -7.2462
Max Act: 6.9337. Min Act: -0.1700
Data Index: 1621644 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2462. Min Range: -7.2462
Max Act: 6.9337. Min Act: -0.1700
Data Index: 3082366 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2462. Min Range: -7.2462
Max Act: 6.9024. Min Act: -0.1700
Data Index: 1660313 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2462. Min Range: -7.2462
Max Act: 6.8712. Min Act: -0.1700
Data Index: 4392072 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2462. Min Range: -7.2462
Max Act: 6.8712. Min Act: -0.1700
Data Index: 8160174 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2462. Min Range: -7.2462
Max Act: 6.7462. Min Act: -0.1700
Data Index: 5441137 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2462. Min Range: -7.2462
Max Act: 6.7149. Min Act: -0.1700
Data Index: 8427148 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2462. Min Range: -7.2462
Max Act: 6.6837. Min Act: -0.1700
Data Index: 4604197 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2462. Min Range: -7.2462
Max Act: 6.6524. Min Act: -0.1700
Data Index: 1953203 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2462. Min Range: -7.2462
Max Act: 6.6524. Min Act: -0.1700
Data Index: 4137105 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2462. Min Range: -7.2462
Max Act: 6.6524. Min Act: -0.1700
Data Index: 8374968 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2462. Min Range: -7.2462
Max Act: 6.6524. Min Act: -0.1700
Data Index: 3828030 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2462. Min Range: -7.2462
Max Act: 6.6524. Min Act: -0.1700
Data Index: 3205812 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2462. Min Range: -7.2462
Max Act: 6.6212. Min Act: -0.1700
Data Index: 7489010 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2462. Min Range: -7.2462
Max Act: 6.5899. Min Act: -0.1700
Data Index: 8416542 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2462. Min Range: -7.2462
Max Act: 6.5587. Min Act: -0.1700
Data Index: 3495042 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2462. Min Range: -7.2462
Max Act: 6.5587. Min Act: -0.1700
Data Index: 481425 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19