Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2655 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1935. Min Range: -6.1935
Max Act: 6.1935. Min Act: -0.1700
Data Index: 5973711 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1935. Min Range: -6.1935
Max Act: 6.1622. Min Act: -0.1700
Data Index: 2995565 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1935. Min Range: -6.1935
Max Act: 5.9122. Min Act: -0.1700
Data Index: 2525384 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1935. Min Range: -6.1935
Max Act: 5.8810. Min Act: -0.1700
Data Index: 4979394 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1935. Min Range: -6.1935
Max Act: 5.7872. Min Act: -0.1700
Data Index: 1072254 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1935. Min Range: -6.1935
Max Act: 5.7560. Min Act: -0.1700
Data Index: 1126788 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1935. Min Range: -6.1935
Max Act: 5.7560. Min Act: -0.1700
Data Index: 1611837 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1935. Min Range: -6.1935
Max Act: 5.6935. Min Act: -0.1700
Data Index: 4366960 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1935. Min Range: -6.1935
Max Act: 5.6935. Min Act: -0.1700
Data Index: 8678991 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1935. Min Range: -6.1935
Max Act: 5.5997. Min Act: -0.1700
Data Index: 1401092 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1935. Min Range: -6.1935
Max Act: 5.5997. Min Act: -0.1700
Data Index: 8697452 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1935. Min Range: -6.1935
Max Act: 5.5997. Min Act: -0.1700
Data Index: 4281994 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1935. Min Range: -6.1935
Max Act: 5.5372. Min Act: -0.1700
Data Index: 6999635 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1935. Min Range: -6.1935
Max Act: 5.5372. Min Act: -0.1700
Data Index: 529294 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1935. Min Range: -6.1935
Max Act: 5.5372. Min Act: -0.1700
Data Index: 1488633 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1935. Min Range: -6.1935
Max Act: 5.5060. Min Act: -0.1700
Data Index: 5115764 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1935. Min Range: -6.1935
Max Act: 5.5060. Min Act: -0.1700
Data Index: 7625128 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1935. Min Range: -6.1935
Max Act: 5.4747. Min Act: -0.1700
Data Index: 3296069 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1935. Min Range: -6.1935
Max Act: 5.4435. Min Act: -0.1700
Data Index: 6061996 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1935. Min Range: -6.1935
Max Act: 5.4747. Min Act: -0.1700
Data Index: 6759911 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19