Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 133 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1088. Min Range: -6.1088
Max Act: 6.1088. Min Act: -0.1699
Data Index: 6378085 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1088. Min Range: -6.1088
Max Act: 6.0151. Min Act: -0.1700
Data Index: 8629769 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1088. Min Range: -6.1088
Max Act: 5.9526. Min Act: -0.1700
Data Index: 745224 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1088. Min Range: -6.1088
Max Act: 5.9213. Min Act: -0.1700
Data Index: 125716 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1088. Min Range: -6.1088
Max Act: 5.9213. Min Act: -0.1700
Data Index: 4194545 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1088. Min Range: -6.1088
Max Act: 5.9213. Min Act: -0.1700
Data Index: 732270 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1088. Min Range: -6.1088
Max Act: 5.8901. Min Act: -0.1700
Data Index: 6859020 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1088. Min Range: -6.1088
Max Act: 5.9213. Min Act: -0.1700
Data Index: 8163342 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1088. Min Range: -6.1088
Max Act: 5.8901. Min Act: -0.1700
Data Index: 6183829 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1088. Min Range: -6.1088
Max Act: 5.8588. Min Act: -0.1700
Data Index: 5474586 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1088. Min Range: -6.1088
Max Act: 5.8901. Min Act: -0.1700
Data Index: 5127380 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1088. Min Range: -6.1088
Max Act: 5.8588. Min Act: -0.1700
Data Index: 172936 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1088. Min Range: -6.1088
Max Act: 5.8276. Min Act: -0.1700
Data Index: 4881007 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1088. Min Range: -6.1088
Max Act: 5.8276. Min Act: -0.1700
Data Index: 5608819 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1088. Min Range: -6.1088
Max Act: 5.8276. Min Act: -0.1700
Data Index: 1694845 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1088. Min Range: -6.1088
Max Act: 5.8276. Min Act: -0.1700
Data Index: 7036708 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1088. Min Range: -6.1088
Max Act: 5.8276. Min Act: -0.1700
Data Index: 2783385 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1088. Min Range: -6.1088
Max Act: 5.7963. Min Act: -0.1700
Data Index: 4744732 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1088. Min Range: -6.1088
Max Act: 5.7963. Min Act: -0.1700
Data Index: 550448 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1088. Min Range: -6.1088
Max Act: 5.7963. Min Act: -0.1700
Data Index: 944967 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19