Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4000 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9180. Min Range: -5.9180
Max Act: 5.9180. Min Act: -0.1700
Data Index: 4744787 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9180. Min Range: -5.9180
Max Act: 5.8242. Min Act: -0.1700
Data Index: 229159 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9180. Min Range: -5.9180
Max Act: 5.7930. Min Act: -0.1700
Data Index: 8126166 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9180. Min Range: -5.9180
Max Act: 5.6055. Min Act: -0.1700
Data Index: 8037973 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9180. Min Range: -5.9180
Max Act: 5.6367. Min Act: -0.1700
Data Index: 7424849 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9180. Min Range: -5.9180
Max Act: 5.6055. Min Act: -0.1700
Data Index: 5980687 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9180. Min Range: -5.9180
Max Act: 5.6055. Min Act: -0.1700
Data Index: 6691198 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9180. Min Range: -5.9180
Max Act: 5.6055. Min Act: -0.1700
Data Index: 525641 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9180. Min Range: -5.9180
Max Act: 5.6055. Min Act: -0.1700
Data Index: 1441955 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9180. Min Range: -5.9180
Max Act: 5.5742. Min Act: -0.1700
Data Index: 7392 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9180. Min Range: -5.9180
Max Act: 5.5430. Min Act: -0.1700
Data Index: 7424848 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9180. Min Range: -5.9180
Max Act: 5.5742. Min Act: -0.1700
Data Index: 67856 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9180. Min Range: -5.9180
Max Act: 5.4805. Min Act: -0.1700
Data Index: 1452988 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9180. Min Range: -5.9180
Max Act: 5.4805. Min Act: -0.1700
Data Index: 5479059 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9180. Min Range: -5.9180
Max Act: 5.4492. Min Act: -0.1700
Data Index: 8195838 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9180. Min Range: -5.9180
Max Act: 5.4492. Min Act: -0.1700
Data Index: 2938760 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9180. Min Range: -5.9180
Max Act: 5.4492. Min Act: -0.1700
Data Index: 6917431 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9180. Min Range: -5.9180
Max Act: 5.4492. Min Act: -0.1700
Data Index: 5961738 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9180. Min Range: -5.9180
Max Act: 5.4180. Min Act: -0.1700
Data Index: 214113 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9180. Min Range: -5.9180
Max Act: 5.4180. Min Act: -0.1700
Data Index: 4870440 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19