Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2866 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7372. Min Range: -6.7372
Max Act: 6.7372. Min Act: -0.1700
Data Index: 2018114 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7372. Min Range: -6.7372
Max Act: 6.7060. Min Act: -0.1700
Data Index: 8563962 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7372. Min Range: -6.7372
Max Act: 6.7060. Min Act: -0.1700
Data Index: 2788991 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7372. Min Range: -6.7372
Max Act: 6.6747. Min Act: -0.1700
Data Index: 1413749 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7372. Min Range: -6.7372
Max Act: 6.6122. Min Act: -0.1700
Data Index: 617961 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7372. Min Range: -6.7372
Max Act: 6.6122. Min Act: -0.1700
Data Index: 4021598 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7372. Min Range: -6.7372
Max Act: 6.6122. Min Act: -0.1700
Data Index: 7617272 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7372. Min Range: -6.7372
Max Act: 6.6122. Min Act: -0.1700
Data Index: 7576985 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7372. Min Range: -6.7372
Max Act: 6.5810. Min Act: -0.1700
Data Index: 787641 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7372. Min Range: -6.7372
Max Act: 6.5810. Min Act: -0.1700
Data Index: 1998645 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7372. Min Range: -6.7372
Max Act: 6.5810. Min Act: -0.1700
Data Index: 7049064 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7372. Min Range: -6.7372
Max Act: 6.6122. Min Act: -0.1700
Data Index: 1694595 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7372. Min Range: -6.7372
Max Act: 6.5810. Min Act: -0.1700
Data Index: 2976466 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7372. Min Range: -6.7372
Max Act: 6.5497. Min Act: -0.1700
Data Index: 3034427 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7372. Min Range: -6.7372
Max Act: 6.5497. Min Act: -0.1700
Data Index: 1771189 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7372. Min Range: -6.7372
Max Act: 6.5497. Min Act: -0.1700
Data Index: 7817825 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7372. Min Range: -6.7372
Max Act: 6.5497. Min Act: -0.1700
Data Index: 4417546 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7372. Min Range: -6.7372
Max Act: 6.5497. Min Act: -0.1700
Data Index: 580991 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7372. Min Range: -6.7372
Max Act: 6.5497. Min Act: -0.1700
Data Index: 5019868 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7372. Min Range: -6.7372
Max Act: 6.5185. Min Act: -0.1700
Data Index: 4505752 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19