Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3618 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5664. Min Range: -7.5664
Max Act: 7.5664. Min Act: -0.1700
Data Index: 8716783 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5664. Min Range: -7.5664
Max Act: 7.4727. Min Act: -0.1700
Data Index: 6160262 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5664. Min Range: -7.5664
Max Act: 7.4102. Min Act: -0.1700
Data Index: 1239463 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5664. Min Range: -7.5664
Max Act: 7.3477. Min Act: -0.1700
Data Index: 7122571 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5664. Min Range: -7.5664
Max Act: 7.1914. Min Act: -0.1700
Data Index: 7896359 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5664. Min Range: -7.5664
Max Act: 7.0352. Min Act: -0.1700
Data Index: 1666458 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5664. Min Range: -7.5664
Max Act: 7.0352. Min Act: -0.1700
Data Index: 3535450 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5664. Min Range: -7.5664
Max Act: 6.8789. Min Act: -0.1700
Data Index: 185274 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5664. Min Range: -7.5664
Max Act: 6.9102. Min Act: -0.1700
Data Index: 410992 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5664. Min Range: -7.5664
Max Act: 6.9414. Min Act: -0.1700
Data Index: 1111093 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5664. Min Range: -7.5664
Max Act: 6.9102. Min Act: -0.1700
Data Index: 4343936 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5664. Min Range: -7.5664
Max Act: 6.8789. Min Act: -0.1700
Data Index: 245799 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5664. Min Range: -7.5664
Max Act: 6.9102. Min Act: -0.1700
Data Index: 8711706 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5664. Min Range: -7.5664
Max Act: 6.8789. Min Act: -0.1700
Data Index: 6739774 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5664. Min Range: -7.5664
Max Act: 6.8789. Min Act: -0.1700
Data Index: 339869 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5664. Min Range: -7.5664
Max Act: 6.8789. Min Act: -0.1700
Data Index: 1285990 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5664. Min Range: -7.5664
Max Act: 6.8477. Min Act: -0.1700
Data Index: 854768 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5664. Min Range: -7.5664
Max Act: 6.8477. Min Act: -0.1700
Data Index: 7268805 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5664. Min Range: -7.5664
Max Act: 6.8477. Min Act: -0.1700
Data Index: 7403097 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5664. Min Range: -7.5664
Max Act: 6.8164. Min Act: -0.1700
Data Index: 4763198 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #19