Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3285 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9165. Min Range: -7.9165
Max Act: 7.9165. Min Act: -0.1700
Data Index: 4738797 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9165. Min Range: -7.9165
Max Act: 7.7915. Min Act: -0.1700
Data Index: 6955988 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9165. Min Range: -7.9165
Max Act: 7.5102. Min Act: -0.1700
Data Index: 2587064 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9165. Min Range: -7.9165
Max Act: 7.5102. Min Act: -0.1700
Data Index: 2587063 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9165. Min Range: -7.9165
Max Act: 7.3540. Min Act: -0.1700
Data Index: 7018105 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9165. Min Range: -7.9165
Max Act: 7.3540. Min Act: -0.1700
Data Index: 1998788 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9165. Min Range: -7.9165
Max Act: 7.3227. Min Act: -0.1700
Data Index: 475351 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9165. Min Range: -7.9165
Max Act: 7.3227. Min Act: -0.1700
Data Index: 4853766 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9165. Min Range: -7.9165
Max Act: 7.1977. Min Act: -0.1700
Data Index: 7374051 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9165. Min Range: -7.9165
Max Act: 7.1665. Min Act: -0.1700
Data Index: 5646752 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9165. Min Range: -7.9165
Max Act: 7.1352. Min Act: -0.1700
Data Index: 7043978 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9165. Min Range: -7.9165
Max Act: 7.1352. Min Act: -0.1700
Data Index: 5942525 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9165. Min Range: -7.9165
Max Act: 7.0727. Min Act: -0.1700
Data Index: 273089 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9165. Min Range: -7.9165
Max Act: 7.0102. Min Act: -0.1700
Data Index: 4682375 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9165. Min Range: -7.9165
Max Act: 7.0102. Min Act: -0.1700
Data Index: 2096910 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9165. Min Range: -7.9165
Max Act: 7.0102. Min Act: -0.1700
Data Index: 1103064 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9165. Min Range: -7.9165
Max Act: 6.9790. Min Act: -0.1700
Data Index: 6946732 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9165. Min Range: -7.9165
Max Act: 6.9790. Min Act: -0.1700
Data Index: 7417442 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9165. Min Range: -7.9165
Max Act: 6.9477. Min Act: -0.1700
Data Index: 4413149 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9165. Min Range: -7.9165
Max Act: 6.9790. Min Act: -0.1700
Data Index: 1114766 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #19