Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3794 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0762. Min Range: -5.0762
Max Act: 5.0762. Min Act: -0.1700
Data Index: 1990986 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0762. Min Range: -5.0762
Max Act: 5.0762. Min Act: -0.1700
Data Index: 4063222 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0762. Min Range: -5.0762
Max Act: 5.0449. Min Act: -0.1700
Data Index: 957937 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0762. Min Range: -5.0762
Max Act: 5.0137. Min Act: -0.1700
Data Index: 5031444 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0762. Min Range: -5.0762
Max Act: 4.9824. Min Act: -0.1700
Data Index: 8304185 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0762. Min Range: -5.0762
Max Act: 4.9824. Min Act: -0.1700
Data Index: 7394404 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0762. Min Range: -5.0762
Max Act: 4.9199. Min Act: -0.1700
Data Index: 4018554 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0762. Min Range: -5.0762
Max Act: 4.9199. Min Act: -0.1700
Data Index: 3601123 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0762. Min Range: -5.0762
Max Act: 4.8574. Min Act: -0.1700
Data Index: 6603894 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0762. Min Range: -5.0762
Max Act: 4.8262. Min Act: -0.1700
Data Index: 5800472 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0762. Min Range: -5.0762
Max Act: 4.7636. Min Act: -0.1700
Data Index: 3617262 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0762. Min Range: -5.0762
Max Act: 4.7949. Min Act: -0.1700
Data Index: 5652055 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0762. Min Range: -5.0762
Max Act: 4.7949. Min Act: -0.1700
Data Index: 5565910 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0762. Min Range: -5.0762
Max Act: 4.7636. Min Act: -0.1700
Data Index: 3773501 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0762. Min Range: -5.0762
Max Act: 4.7636. Min Act: -0.1700
Data Index: 2861408 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0762. Min Range: -5.0762
Max Act: 4.7011. Min Act: -0.1700
Data Index: 2739629 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0762. Min Range: -5.0762
Max Act: 4.7011. Min Act: -0.1700
Data Index: 456298 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0762. Min Range: -5.0762
Max Act: 4.6699. Min Act: -0.1700
Data Index: 1769284 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0762. Min Range: -5.0762
Max Act: 4.6386. Min Act: -0.1700
Data Index: 632051 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0762. Min Range: -5.0762
Max Act: 4.6699. Min Act: -0.1700
Data Index: 2245849 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #19