Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5778 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6907. Min Range: -6.6907
Max Act: 6.6907. Min Act: -0.1700
Data Index: 658113 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6907. Min Range: -6.6907
Max Act: 6.6594. Min Act: -0.1700
Data Index: 1690957 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6907. Min Range: -6.6907
Max Act: 6.5969. Min Act: -0.1700
Data Index: 6481668 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6907. Min Range: -6.6907
Max Act: 6.5969. Min Act: -0.1700
Data Index: 6109280 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6907. Min Range: -6.6907
Max Act: 6.5969. Min Act: -0.1700
Data Index: 6710485 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6907. Min Range: -6.6907
Max Act: 6.5969. Min Act: -0.1700
Data Index: 4837433 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6907. Min Range: -6.6907
Max Act: 6.5657. Min Act: -0.1700
Data Index: 1533865 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6907. Min Range: -6.6907
Max Act: 6.5657. Min Act: -0.1700
Data Index: 4837443 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6907. Min Range: -6.6907
Max Act: 6.5657. Min Act: -0.1700
Data Index: 6038249 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6907. Min Range: -6.6907
Max Act: 6.5344. Min Act: -0.1700
Data Index: 3101958 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6907. Min Range: -6.6907
Max Act: 6.5344. Min Act: -0.1700
Data Index: 2800865 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6907. Min Range: -6.6907
Max Act: 6.5032. Min Act: -0.1700
Data Index: 2379332 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6907. Min Range: -6.6907
Max Act: 6.5032. Min Act: -0.1700
Data Index: 6542462 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6907. Min Range: -6.6907
Max Act: 6.5344. Min Act: -0.1700
Data Index: 2379331 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6907. Min Range: -6.6907
Max Act: 6.4719. Min Act: -0.1700
Data Index: 8050043 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6907. Min Range: -6.6907
Max Act: 6.4719. Min Act: -0.1700
Data Index: 663086 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6907. Min Range: -6.6907
Max Act: 6.4407. Min Act: -0.1700
Data Index: 7047810 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6907. Min Range: -6.6907
Max Act: 6.4407. Min Act: -0.1700
Data Index: 2751650 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6907. Min Range: -6.6907
Max Act: 6.4407. Min Act: -0.1700
Data Index: 4426041 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6907. Min Range: -6.6907
Max Act: 6.4407. Min Act: -0.1700
Data Index: 4679910 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19