Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2828 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6062. Min Range: -8.6062
Max Act: 8.6062. Min Act: -0.1700
Data Index: 4126825 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6062. Min Range: -8.6062
Max Act: 8.1687. Min Act: -0.1700
Data Index: 1867255 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6062. Min Range: -8.6062
Max Act: 8.1375. Min Act: -0.1700
Data Index: 5408784 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6062. Min Range: -8.6062
Max Act: 7.7625. Min Act: -0.1700
Data Index: 1256041 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6062. Min Range: -8.6062
Max Act: 7.6062. Min Act: -0.1700
Data Index: 5999751 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6062. Min Range: -8.6062
Max Act: 7.6375. Min Act: -0.1700
Data Index: 785967 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6062. Min Range: -8.6062
Max Act: 7.5437. Min Act: -0.1700
Data Index: 493921 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6062. Min Range: -8.6062
Max Act: 7.4812. Min Act: -0.1700
Data Index: 6741728 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6062. Min Range: -8.6062
Max Act: 7.4812. Min Act: -0.1700
Data Index: 7677651 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6062. Min Range: -8.6062
Max Act: 7.4187. Min Act: -0.1700
Data Index: 8253524 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6062. Min Range: -8.6062
Max Act: 7.4187. Min Act: -0.1700
Data Index: 3777679 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6062. Min Range: -8.6062
Max Act: 7.3250. Min Act: -0.1700
Data Index: 1537727 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6062. Min Range: -8.6062
Max Act: 7.3562. Min Act: -0.1700
Data Index: 1242804 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6062. Min Range: -8.6062
Max Act: 7.3562. Min Act: -0.1700
Data Index: 7836702 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6062. Min Range: -8.6062
Max Act: 7.3250. Min Act: -0.1700
Data Index: 6603335 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6062. Min Range: -8.6062
Max Act: 7.3250. Min Act: -0.1700
Data Index: 1817571 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6062. Min Range: -8.6062
Max Act: 7.2937. Min Act: -0.1700
Data Index: 6492757 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6062. Min Range: -8.6062
Max Act: 7.2937. Min Act: -0.1700
Data Index: 3315686 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6062. Min Range: -8.6062
Max Act: 7.2937. Min Act: -0.1700
Data Index: 1139649 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6062. Min Range: -8.6062
Max Act: 7.2937. Min Act: -0.1700
Data Index: 7787558 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #19