Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 232 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5078. Min Range: -6.5078
Max Act: 6.5078. Min Act: -0.1700
Data Index: 4733413 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5078. Min Range: -6.5078
Max Act: 6.4141. Min Act: -0.1700
Data Index: 8541097 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5078. Min Range: -6.5078
Max Act: 6.4141. Min Act: -0.1700
Data Index: 3768609 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5078. Min Range: -6.5078
Max Act: 6.3516. Min Act: -0.1700
Data Index: 3206579 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5078. Min Range: -6.5078
Max Act: 6.3516. Min Act: -0.1700
Data Index: 1659734 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5078. Min Range: -6.5078
Max Act: 6.2891. Min Act: -0.1700
Data Index: 4169688 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5078. Min Range: -6.5078
Max Act: 6.2891. Min Act: -0.1700
Data Index: 4234636 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5078. Min Range: -6.5078
Max Act: 6.2266. Min Act: -0.1700
Data Index: 3206580 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5078. Min Range: -6.5078
Max Act: 6.1641. Min Act: -0.1700
Data Index: 7102158 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5078. Min Range: -6.5078
Max Act: 6.1953. Min Act: -0.1700
Data Index: 2774227 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5078. Min Range: -6.5078
Max Act: 6.1641. Min Act: -0.1700
Data Index: 3381119 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5078. Min Range: -6.5078
Max Act: 6.1953. Min Act: -0.1700
Data Index: 53220 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5078. Min Range: -6.5078
Max Act: 6.1328. Min Act: -0.1700
Data Index: 3851949 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5078. Min Range: -6.5078
Max Act: 6.1328. Min Act: -0.1700
Data Index: 910267 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5078. Min Range: -6.5078
Max Act: 6.1328. Min Act: -0.1700
Data Index: 4157180 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5078. Min Range: -6.5078
Max Act: 6.1328. Min Act: -0.1700
Data Index: 5238955 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5078. Min Range: -6.5078
Max Act: 6.1328. Min Act: -0.1700
Data Index: 6205125 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5078. Min Range: -6.5078
Max Act: 6.1016. Min Act: -0.1700
Data Index: 5543655 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5078. Min Range: -6.5078
Max Act: 6.0703. Min Act: -0.1700
Data Index: 6400015 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5078. Min Range: -6.5078
Max Act: 6.0703. Min Act: -0.1700
Data Index: 8515165 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19