Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4441 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0907. Min Range: -5.0907
Max Act: 5.0907. Min Act: -0.1700
Data Index: 8698726 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0907. Min Range: -5.0907
Max Act: 5.0594. Min Act: -0.1700
Data Index: 6083646 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0907. Min Range: -5.0907
Max Act: 4.9657. Min Act: -0.1700
Data Index: 6718490 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0907. Min Range: -5.0907
Max Act: 4.9344. Min Act: -0.1700
Data Index: 2382379 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0907. Min Range: -5.0907
Max Act: 4.9344. Min Act: -0.1700
Data Index: 3137421 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0907. Min Range: -5.0907
Max Act: 4.9344. Min Act: -0.1700
Data Index: 2733605 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0907. Min Range: -5.0907
Max Act: 4.9032. Min Act: -0.1700
Data Index: 1926936 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0907. Min Range: -5.0907
Max Act: 4.9032. Min Act: -0.1700
Data Index: 8309075 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0907. Min Range: -5.0907
Max Act: 4.9032. Min Act: -0.1700
Data Index: 231720 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0907. Min Range: -5.0907
Max Act: 4.8719. Min Act: -0.1700
Data Index: 4706650 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0907. Min Range: -5.0907
Max Act: 4.8719. Min Act: -0.1700
Data Index: 5288255 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0907. Min Range: -5.0907
Max Act: 4.8719. Min Act: -0.1700
Data Index: 3596691 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0907. Min Range: -5.0907
Max Act: 4.8719. Min Act: -0.1700
Data Index: 1071201 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0907. Min Range: -5.0907
Max Act: 4.8719. Min Act: -0.1700
Data Index: 7042693 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0907. Min Range: -5.0907
Max Act: 4.8719. Min Act: -0.1700
Data Index: 8309074 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0907. Min Range: -5.0907
Max Act: 4.8407. Min Act: -0.1700
Data Index: 6280482 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0907. Min Range: -5.0907
Max Act: 4.8407. Min Act: -0.1700
Data Index: 4224103 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0907. Min Range: -5.0907
Max Act: 4.8407. Min Act: -0.1700
Data Index: 3523450 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0907. Min Range: -5.0907
Max Act: 4.8407. Min Act: -0.1700
Data Index: 5782424 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0907. Min Range: -5.0907
Max Act: 4.8407. Min Act: -0.1700
Data Index: 5241535 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #19