Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3794 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5040. Min Range: -6.5040
Max Act: 6.4727. Min Act: -0.1700
Data Index: 3559885 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5040. Min Range: -6.5040
Max Act: 6.5040. Min Act: -0.1700
Data Index: 4046731 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5040. Min Range: -6.5040
Max Act: 6.4102. Min Act: -0.1700
Data Index: 6591698 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5040. Min Range: -6.5040
Max Act: 6.2227. Min Act: -0.1700
Data Index: 3621280 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5040. Min Range: -6.5040
Max Act: 6.0352. Min Act: -0.1700
Data Index: 1556712 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5040. Min Range: -6.5040
Max Act: 6.0040. Min Act: -0.1700
Data Index: 1918128 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5040. Min Range: -6.5040
Max Act: 5.9727. Min Act: -0.1700
Data Index: 4022070 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5040. Min Range: -6.5040
Max Act: 5.9415. Min Act: -0.1700
Data Index: 8326811 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5040. Min Range: -6.5040
Max Act: 5.8790. Min Act: -0.1700
Data Index: 6046819 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5040. Min Range: -6.5040
Max Act: 5.8165. Min Act: -0.1700
Data Index: 8603495 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5040. Min Range: -6.5040
Max Act: 5.8477. Min Act: -0.1700
Data Index: 2847690 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5040. Min Range: -6.5040
Max Act: 5.8477. Min Act: -0.1700
Data Index: 6359046 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5040. Min Range: -6.5040
Max Act: 5.8477. Min Act: -0.1700
Data Index: 6375885 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5040. Min Range: -6.5040
Max Act: 5.8477. Min Act: -0.1700
Data Index: 3076256 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5040. Min Range: -6.5040
Max Act: 5.8477. Min Act: -0.1700
Data Index: 5752599 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5040. Min Range: -6.5040
Max Act: 5.8165. Min Act: -0.1700
Data Index: 4276043 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5040. Min Range: -6.5040
Max Act: 5.8165. Min Act: -0.1700
Data Index: 3589573 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5040. Min Range: -6.5040
Max Act: 5.8477. Min Act: -0.1700
Data Index: 5700665 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5040. Min Range: -6.5040
Max Act: 5.8165. Min Act: -0.1700
Data Index: 6375886 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5040. Min Range: -6.5040
Max Act: 5.7852. Min Act: -0.1700
Data Index: 4071903 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19