Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 17 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.2947. Min Act: -0.1700
Data Index: 4997783 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.2634. Min Act: -0.1700
Data Index: 5304866 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.2009. Min Act: -0.1700
Data Index: 2181370 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.1697. Min Act: -0.1700
Data Index: 8114272 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.1697. Min Act: -0.1700
Data Index: 3375316 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.1072. Min Act: -0.1700
Data Index: 4194919 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.1072. Min Act: -0.1700
Data Index: 1598364 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.0759. Min Act: -0.1700
Data Index: 5823642 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.0759. Min Act: -0.1700
Data Index: 3251769 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.0759. Min Act: -0.1700
Data Index: 2831286 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.0759. Min Act: -0.1700
Data Index: 8563131 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.0446. Min Act: -0.1700
Data Index: 6899322 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.0446. Min Act: -0.1700
Data Index: 4364431 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.0446. Min Act: -0.1700
Data Index: 5427175 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2947. Min Range: -4.2947
Max Act: 3.9821. Min Act: -0.1700
Data Index: 4989428 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.0134. Min Act: -0.1700
Data Index: 5179338 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.0134. Min Act: -0.1700
Data Index: 5569239 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2947. Min Range: -4.2947
Max Act: 3.9821. Min Act: -0.1700
Data Index: 4752130 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2947. Min Range: -4.2947
Max Act: 3.9821. Min Act: -0.1700
Data Index: 3600348 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2947. Min Range: -4.2947
Max Act: 3.9821. Min Act: -0.1700
Data Index: 604634 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19