Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3133 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1077. Min Range: -5.1077
Max Act: 5.1077. Min Act: -0.1700
Data Index: 5255834 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1077. Min Range: -5.1077
Max Act: 5.1077. Min Act: -0.1700
Data Index: 609211 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1077. Min Range: -5.1077
Max Act: 5.0452. Min Act: -0.1700
Data Index: 6788839 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1077. Min Range: -5.1077
Max Act: 4.9514. Min Act: -0.1700
Data Index: 8414617 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1077. Min Range: -5.1077
Max Act: 4.9202. Min Act: -0.1700
Data Index: 6173849 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1077. Min Range: -5.1077
Max Act: 4.9202. Min Act: -0.1700
Data Index: 3140148 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1077. Min Range: -5.1077
Max Act: 4.8889. Min Act: -0.1700
Data Index: 3180887 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1077. Min Range: -5.1077
Max Act: 4.8577. Min Act: -0.1700
Data Index: 5114205 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1077. Min Range: -5.1077
Max Act: 4.8577. Min Act: -0.1700
Data Index: 6753312 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1077. Min Range: -5.1077
Max Act: 4.8577. Min Act: -0.1700
Data Index: 5504652 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1077. Min Range: -5.1077
Max Act: 4.8264. Min Act: -0.1700
Data Index: 2403711 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1077. Min Range: -5.1077
Max Act: 4.8264. Min Act: -0.1700
Data Index: 7042179 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1077. Min Range: -5.1077
Max Act: 4.8264. Min Act: -0.1700
Data Index: 4418977 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1077. Min Range: -5.1077
Max Act: 4.8264. Min Act: -0.1700
Data Index: 3173739 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1077. Min Range: -5.1077
Max Act: 4.7639. Min Act: -0.1700
Data Index: 7547257 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1077. Min Range: -5.1077
Max Act: 4.7952. Min Act: -0.1700
Data Index: 2015036 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1077. Min Range: -5.1077
Max Act: 4.7952. Min Act: -0.1700
Data Index: 5492940 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1077. Min Range: -5.1077
Max Act: 4.7952. Min Act: -0.1700
Data Index: 270981 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1077. Min Range: -5.1077
Max Act: 4.7639. Min Act: -0.1700
Data Index: 6674522 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1077. Min Range: -5.1077
Max Act: 4.7639. Min Act: -0.1700
Data Index: 6549255 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #19