Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4443 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1141. Min Range: -8.1141
Max Act: 8.1141. Min Act: -0.1700
Data Index: 4724152 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1141. Min Range: -8.1141
Max Act: 7.9266. Min Act: -0.1700
Data Index: 8120920 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1141. Min Range: -8.1141
Max Act: 7.8328. Min Act: -0.1700
Data Index: 5545037 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1141. Min Range: -8.1141
Max Act: 7.8641. Min Act: -0.1700
Data Index: 3193477 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1141. Min Range: -8.1141
Max Act: 7.8328. Min Act: -0.1692
Data Index: 7174856 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1141. Min Range: -8.1141
Max Act: 7.7703. Min Act: -0.1673
Data Index: 4954511 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1141. Min Range: -8.1141
Max Act: 7.7391. Min Act: -0.1699
Data Index: 42252 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1141. Min Range: -8.1141
Max Act: 7.6766. Min Act: -0.1700
Data Index: 1936553 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1141. Min Range: -8.1141
Max Act: 7.6453. Min Act: -0.1700
Data Index: 5975961 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1141. Min Range: -8.1141
Max Act: 7.6141. Min Act: -0.1700
Data Index: 7477497 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1141. Min Range: -8.1141
Max Act: 7.6141. Min Act: -0.1657
Data Index: 4954501 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1141. Min Range: -8.1141
Max Act: 7.5516. Min Act: -0.1700
Data Index: 3784352 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1141. Min Range: -8.1141
Max Act: 7.5203. Min Act: -0.1700
Data Index: 4734634 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1141. Min Range: -8.1141
Max Act: 7.4891. Min Act: -0.1700
Data Index: 5155565 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1141. Min Range: -8.1141
Max Act: 7.4266. Min Act: -0.1700
Data Index: 6710728 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1141. Min Range: -8.1141
Max Act: 7.3328. Min Act: -0.1700
Data Index: 4106990 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1141. Min Range: -8.1141
Max Act: 7.3016. Min Act: -0.1700
Data Index: 7564026 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1141. Min Range: -8.1141
Max Act: 7.3328. Min Act: -0.1700
Data Index: 4842728 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1141. Min Range: -8.1141
Max Act: 7.3328. Min Act: -0.1698
Data Index: 2109377 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1141. Min Range: -8.1141
Max Act: 7.3016. Min Act: -0.1699
Data Index: 3041562 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #19