Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3550 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0465. Min Range: -6.0465
Max Act: 6.0465. Min Act: -0.1700
Data Index: 1221461 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0465. Min Range: -6.0465
Max Act: 5.8590. Min Act: -0.1700
Data Index: 1777949 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0465. Min Range: -6.0465
Max Act: 5.7028. Min Act: -0.1700
Data Index: 6353766 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0465. Min Range: -6.0465
Max Act: 5.6715. Min Act: -0.1700
Data Index: 1515302 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0465. Min Range: -6.0465
Max Act: 5.6715. Min Act: -0.1700
Data Index: 1515299 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0465. Min Range: -6.0465
Max Act: 5.6403. Min Act: -0.1700
Data Index: 7833770 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0465. Min Range: -6.0465
Max Act: 5.6403. Min Act: -0.1700
Data Index: 5998299 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0465. Min Range: -6.0465
Max Act: 5.6403. Min Act: -0.1700
Data Index: 4257841 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0465. Min Range: -6.0465
Max Act: 5.6090. Min Act: -0.1700
Data Index: 4772072 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0465. Min Range: -6.0465
Max Act: 5.6403. Min Act: -0.1700
Data Index: 6004446 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0465. Min Range: -6.0465
Max Act: 5.6090. Min Act: -0.1700
Data Index: 6805464 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0465. Min Range: -6.0465
Max Act: 5.5778. Min Act: -0.1700
Data Index: 1180044 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0465. Min Range: -6.0465
Max Act: 5.5778. Min Act: -0.1700
Data Index: 5754737 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0465. Min Range: -6.0465
Max Act: 5.5778. Min Act: -0.1700
Data Index: 4720525 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0465. Min Range: -6.0465
Max Act: 5.5778. Min Act: -0.1700
Data Index: 788276 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0465. Min Range: -6.0465
Max Act: 5.5465. Min Act: -0.1700
Data Index: 7898602 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0465. Min Range: -6.0465
Max Act: 5.5465. Min Act: -0.1700
Data Index: 7247768 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0465. Min Range: -6.0465
Max Act: 5.5778. Min Act: -0.1700
Data Index: 7150234 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0465. Min Range: -6.0465
Max Act: 5.5465. Min Act: -0.1700
Data Index: 779548 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0465. Min Range: -6.0465
Max Act: 5.5465. Min Act: -0.1700
Data Index: 1160634 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19