Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5967 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7137. Min Range: -6.7137
Max Act: 6.7137. Min Act: -0.1700
Data Index: 5036988 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7137. Min Range: -6.7137
Max Act: 6.6512. Min Act: -0.1700
Data Index: 5036989 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7137. Min Range: -6.7137
Max Act: 6.6512. Min Act: -0.1700
Data Index: 2174267 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7137. Min Range: -6.7137
Max Act: 6.5262. Min Act: -0.1700
Data Index: 7575198 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7137. Min Range: -6.7137
Max Act: 6.5262. Min Act: -0.1700
Data Index: 3235592 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7137. Min Range: -6.7137
Max Act: 6.4949. Min Act: -0.1700
Data Index: 8493183 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7137. Min Range: -6.7137
Max Act: 6.4637. Min Act: -0.1700
Data Index: 7977513 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7137. Min Range: -6.7137
Max Act: 6.4637. Min Act: -0.1700
Data Index: 3178525 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7137. Min Range: -6.7137
Max Act: 6.4012. Min Act: -0.1700
Data Index: 8032514 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7137. Min Range: -6.7137
Max Act: 6.4324. Min Act: -0.1700
Data Index: 5870418 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7137. Min Range: -6.7137
Max Act: 6.3699. Min Act: -0.1700
Data Index: 2350216 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7137. Min Range: -6.7137
Max Act: 6.3699. Min Act: -0.1700
Data Index: 3578225 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7137. Min Range: -6.7137
Max Act: 6.3699. Min Act: -0.1700
Data Index: 7085688 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7137. Min Range: -6.7137
Max Act: 6.3387. Min Act: -0.1700
Data Index: 6017254 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7137. Min Range: -6.7137
Max Act: 6.3387. Min Act: -0.1700
Data Index: 2694406 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7137. Min Range: -6.7137
Max Act: 6.3387. Min Act: -0.1700
Data Index: 2838980 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7137. Min Range: -6.7137
Max Act: 6.3387. Min Act: -0.1700
Data Index: 2704930 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7137. Min Range: -6.7137
Max Act: 6.3074. Min Act: -0.1700
Data Index: 4920746 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7137. Min Range: -6.7137
Max Act: 6.3074. Min Act: -0.1700
Data Index: 2728096 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7137. Min Range: -6.7137
Max Act: 6.3074. Min Act: -0.1700
Data Index: 2694403 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19