Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6377 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0745. Min Range: -7.0745
Max Act: 7.0745. Min Act: -0.1700
Data Index: 7562733 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0745. Min Range: -7.0745
Max Act: 7.0745. Min Act: -0.1700
Data Index: 1925653 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0745. Min Range: -7.0745
Max Act: 6.9495. Min Act: -0.1700
Data Index: 7259401 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0745. Min Range: -7.0745
Max Act: 6.9495. Min Act: -0.1700
Data Index: 324509 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0745. Min Range: -7.0745
Max Act: 6.8870. Min Act: -0.1700
Data Index: 8159142 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0745. Min Range: -7.0745
Max Act: 6.8245. Min Act: -0.1700
Data Index: 1925658 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0745. Min Range: -7.0745
Max Act: 6.7620. Min Act: -0.1700
Data Index: 8543195 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0745. Min Range: -7.0745
Max Act: 6.7620. Min Act: -0.1700
Data Index: 2914571 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0745. Min Range: -7.0745
Max Act: 6.7620. Min Act: -0.1700
Data Index: 3835146 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0745. Min Range: -7.0745
Max Act: 6.7620. Min Act: -0.1700
Data Index: 7527740 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0745. Min Range: -7.0745
Max Act: 6.7620. Min Act: -0.1700
Data Index: 7562728 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0745. Min Range: -7.0745
Max Act: 6.6995. Min Act: -0.1700
Data Index: 6818802 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0745. Min Range: -7.0745
Max Act: 6.6995. Min Act: -0.1700
Data Index: 8779549 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0745. Min Range: -7.0745
Max Act: 6.6683. Min Act: -0.1700
Data Index: 7562727 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0745. Min Range: -7.0745
Max Act: 6.6370. Min Act: -0.1700
Data Index: 1487259 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0745. Min Range: -7.0745
Max Act: 6.6683. Min Act: -0.1700
Data Index: 6678025 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0745. Min Range: -7.0745
Max Act: 6.6683. Min Act: -0.1700
Data Index: 3087371 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0745. Min Range: -7.0745
Max Act: 6.6370. Min Act: -0.1700
Data Index: 3436224 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0745. Min Range: -7.0745
Max Act: 6.6370. Min Act: -0.1700
Data Index: 8382592 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0745. Min Range: -7.0745
Max Act: 6.6370. Min Act: -0.1700
Data Index: 4884258 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19