Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4172 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4898. Min Range: -6.4898
Max Act: 6.4898. Min Act: -0.1700
Data Index: 875156 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4898. Min Range: -6.4898
Max Act: 6.3648. Min Act: -0.1700
Data Index: 5224090 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4898. Min Range: -6.4898
Max Act: 6.3023. Min Act: -0.1700
Data Index: 7677776 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4898. Min Range: -6.4898
Max Act: 6.3023. Min Act: -0.1700
Data Index: 6198985 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4898. Min Range: -6.4898
Max Act: 6.2398. Min Act: -0.1700
Data Index: 7203036 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4898. Min Range: -6.4898
Max Act: 6.2398. Min Act: -0.1700
Data Index: 2608775 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4898. Min Range: -6.4898
Max Act: 6.2085. Min Act: -0.1700
Data Index: 7590772 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4898. Min Range: -6.4898
Max Act: 6.1773. Min Act: -0.1700
Data Index: 1542518 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4898. Min Range: -6.4898
Max Act: 6.1773. Min Act: -0.1700
Data Index: 2670902 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4898. Min Range: -6.4898
Max Act: 6.1148. Min Act: -0.1700
Data Index: 2733800 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4898. Min Range: -6.4898
Max Act: 6.0835. Min Act: -0.1700
Data Index: 6723827 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4898. Min Range: -6.4898
Max Act: 6.0210. Min Act: -0.1700
Data Index: 4491116 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4898. Min Range: -6.4898
Max Act: 6.0210. Min Act: -0.1700
Data Index: 7925609 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4898. Min Range: -6.4898
Max Act: 5.9898. Min Act: -0.1700
Data Index: 8269723 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4898. Min Range: -6.4898
Max Act: 5.9898. Min Act: -0.1700
Data Index: 8322385 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4898. Min Range: -6.4898
Max Act: 5.9898. Min Act: -0.1700
Data Index: 5044664 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4898. Min Range: -6.4898
Max Act: 5.9898. Min Act: -0.1700
Data Index: 7935518 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4898. Min Range: -6.4898
Max Act: 5.9585. Min Act: -0.1700
Data Index: 6033563 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4898. Min Range: -6.4898
Max Act: 5.9585. Min Act: -0.1700
Data Index: 6200322 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4898. Min Range: -6.4898
Max Act: 5.9585. Min Act: -0.1700
Data Index: 7128373 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #19