Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2684 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2962. Min Range: -4.2962
Max Act: 4.2962. Min Act: -0.1700
Data Index: 4408455 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2962. Min Range: -4.2962
Max Act: 4.1086. Min Act: -0.1700
Data Index: 5038136 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2962. Min Range: -4.2962
Max Act: 4.0149. Min Act: -0.1700
Data Index: 4170976 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2962. Min Range: -4.2962
Max Act: 3.9836. Min Act: -0.1700
Data Index: 3583748 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2962. Min Range: -4.2962
Max Act: 3.9211. Min Act: -0.1700
Data Index: 8611344 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2962. Min Range: -4.2962
Max Act: 3.8898. Min Act: -0.1700
Data Index: 1475447 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2962. Min Range: -4.2962
Max Act: 3.9211. Min Act: -0.1700
Data Index: 4539340 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2962. Min Range: -4.2962
Max Act: 3.9211. Min Act: -0.1700
Data Index: 2701117 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2962. Min Range: -4.2962
Max Act: 3.8898. Min Act: -0.1700
Data Index: 3856823 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2962. Min Range: -4.2962
Max Act: 3.8898. Min Act: -0.1700
Data Index: 8032867 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2962. Min Range: -4.2962
Max Act: 3.9211. Min Act: -0.1700
Data Index: 4182579 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2962. Min Range: -4.2962
Max Act: 3.8898. Min Act: -0.1700
Data Index: 8416674 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2962. Min Range: -4.2962
Max Act: 3.8585. Min Act: -0.1700
Data Index: 3734490 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2962. Min Range: -4.2962
Max Act: 3.8585. Min Act: -0.1700
Data Index: 8604341 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2962. Min Range: -4.2962
Max Act: 3.8273. Min Act: -0.1700
Data Index: 232635 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2962. Min Range: -4.2962
Max Act: 3.8273. Min Act: -0.1700
Data Index: 4396425 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2962. Min Range: -4.2962
Max Act: 3.7960. Min Act: -0.1700
Data Index: 349017 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2962. Min Range: -4.2962
Max Act: 3.7960. Min Act: -0.1700
Data Index: 2604345 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2962. Min Range: -4.2962
Max Act: 3.7960. Min Act: -0.1700
Data Index: 4611744 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2962. Min Range: -4.2962
Max Act: 3.7960. Min Act: -0.1700
Data Index: 7035045 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19