Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2804 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8823. Min Range: -6.8823
Max Act: 6.8823. Min Act: -0.1700
Data Index: 2558311 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8823. Min Range: -6.8823
Max Act: 6.6636. Min Act: -0.1700
Data Index: 5596593 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8823. Min Range: -6.8823
Max Act: 6.6636. Min Act: -0.1700
Data Index: 205029 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8823. Min Range: -6.8823
Max Act: 6.5073. Min Act: -0.1700
Data Index: 2457120 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8823. Min Range: -6.8823
Max Act: 6.4448. Min Act: -0.1700
Data Index: 499619 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8823. Min Range: -6.8823
Max Act: 6.4136. Min Act: -0.1700
Data Index: 1755193 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8823. Min Range: -6.8823
Max Act: 6.3823. Min Act: -0.1700
Data Index: 1687111 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8823. Min Range: -6.8823
Max Act: 6.4136. Min Act: -0.1700
Data Index: 7684468 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8823. Min Range: -6.8823
Max Act: 6.4136. Min Act: -0.1700
Data Index: 3518415 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8823. Min Range: -6.8823
Max Act: 6.3823. Min Act: -0.1700
Data Index: 7688883 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8823. Min Range: -6.8823
Max Act: 6.3511. Min Act: -0.1700
Data Index: 6260869 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8823. Min Range: -6.8823
Max Act: 6.3511. Min Act: -0.1700
Data Index: 5116832 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8823. Min Range: -6.8823
Max Act: 6.2886. Min Act: -0.1700
Data Index: 6022046 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8823. Min Range: -6.8823
Max Act: 6.2886. Min Act: -0.1700
Data Index: 41660 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8823. Min Range: -6.8823
Max Act: 6.2886. Min Act: -0.1700
Data Index: 3253709 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8823. Min Range: -6.8823
Max Act: 6.2886. Min Act: -0.1700
Data Index: 7048822 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8823. Min Range: -6.8823
Max Act: 6.2886. Min Act: -0.1700
Data Index: 150284 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8823. Min Range: -6.8823
Max Act: 6.2573. Min Act: -0.1700
Data Index: 5251587 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8823. Min Range: -6.8823
Max Act: 6.2886. Min Act: -0.1700
Data Index: 5512087 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8823. Min Range: -6.8823
Max Act: 6.2573. Min Act: -0.1700
Data Index: 3734826 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #19