Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5714 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.4029. Min Range: -12.4029
Max Act: 12.4029. Min Act: -0.1700
Data Index: 3146853 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.4029. Min Range: -12.4029
Max Act: 12.2154. Min Act: -0.1700
Data Index: 4253009 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.4029. Min Range: -12.4029
Max Act: 12.0279. Min Act: -0.1700
Data Index: 564751 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.4029. Min Range: -12.4029
Max Act: 11.8404. Min Act: -0.1700
Data Index: 4030401 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.4029. Min Range: -12.4029
Max Act: 11.8404. Min Act: -0.1700
Data Index: 6331581 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.4029. Min Range: -12.4029
Max Act: 11.8404. Min Act: -0.1700
Data Index: 6751900 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.4029. Min Range: -12.4029
Max Act: 11.8404. Min Act: -0.1700
Data Index: 4965505 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.4029. Min Range: -12.4029
Max Act: 11.8404. Min Act: -0.1700
Data Index: 2488143 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.4029. Min Range: -12.4029
Max Act: 11.7779. Min Act: -0.1700
Data Index: 4125178 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.4029. Min Range: -12.4029
Max Act: 11.6529. Min Act: -0.1700
Data Index: 7207593 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.4029. Min Range: -12.4029
Max Act: 11.6529. Min Act: -0.1700
Data Index: 6030078 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.4029. Min Range: -12.4029
Max Act: 11.6529. Min Act: -0.1700
Data Index: 2732159 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.4029. Min Range: -12.4029
Max Act: 11.6529. Min Act: -0.1700
Data Index: 303574 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.4029. Min Range: -12.4029
Max Act: 11.5904. Min Act: -0.1700
Data Index: 1411778 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.4029. Min Range: -12.4029
Max Act: 11.5904. Min Act: -0.1700
Data Index: 262277 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.4029. Min Range: -12.4029
Max Act: 11.5279. Min Act: -0.1700
Data Index: 7511824 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.4029. Min Range: -12.4029
Max Act: 11.5279. Min Act: -0.1700
Data Index: 5268873 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.4029. Min Range: -12.4029
Max Act: 11.4029. Min Act: -0.1700
Data Index: 443574 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.4029. Min Range: -12.4029
Max Act: 11.4654. Min Act: -0.1700
Data Index: 6870981 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.4029. Min Range: -12.4029
Max Act: 11.4029. Min Act: -0.1700
Data Index: 3598577 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #19