Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2193 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1603. Min Range: -6.1603
Max Act: 6.1603. Min Act: -0.1700
Data Index: 5544789 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1603. Min Range: -6.1603
Max Act: 6.0353. Min Act: -0.1700
Data Index: 7115847 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1603. Min Range: -6.1603
Max Act: 6.0040. Min Act: -0.1700
Data Index: 4861495 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1603. Min Range: -6.1603
Max Act: 6.0665. Min Act: -0.1700
Data Index: 6087346 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1603. Min Range: -6.1603
Max Act: 6.0040. Min Act: -0.1700
Data Index: 4454197 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1603. Min Range: -6.1603
Max Act: 5.9728. Min Act: -0.1700
Data Index: 1182718 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1603. Min Range: -6.1603
Max Act: 5.9103. Min Act: -0.1700
Data Index: 6821637 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1603. Min Range: -6.1603
Max Act: 5.8790. Min Act: -0.1700
Data Index: 7852387 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1603. Min Range: -6.1603
Max Act: 5.9103. Min Act: -0.1700
Data Index: 7933680 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1603. Min Range: -6.1603
Max Act: 5.8478. Min Act: -0.1700
Data Index: 3033475 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1603. Min Range: -6.1603
Max Act: 5.8478. Min Act: -0.1700
Data Index: 8472594 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1603. Min Range: -6.1603
Max Act: 5.8790. Min Act: -0.1700
Data Index: 7261845 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1603. Min Range: -6.1603
Max Act: 5.8165. Min Act: -0.1700
Data Index: 3445851 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1603. Min Range: -6.1603
Max Act: 5.8165. Min Act: -0.1700
Data Index: 580760 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1603. Min Range: -6.1603
Max Act: 5.8165. Min Act: -0.1700
Data Index: 6225408 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1603. Min Range: -6.1603
Max Act: 5.7853. Min Act: -0.1700
Data Index: 6662809 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1603. Min Range: -6.1603
Max Act: 5.7853. Min Act: -0.1700
Data Index: 5850895 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1603. Min Range: -6.1603
Max Act: 5.8165. Min Act: -0.1700
Data Index: 1264156 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1603. Min Range: -6.1603
Max Act: 5.7540. Min Act: -0.1700
Data Index: 6038250 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1603. Min Range: -6.1603
Max Act: 5.7540. Min Act: -0.1700
Data Index: 6101259 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #19