Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3967 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.5767. Min Act: -0.1700
Data Index: 7993869 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.5767. Min Act: -0.1700
Data Index: 3121931 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.3892. Min Act: -0.1700
Data Index: 2375672 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.3892. Min Act: -0.1700
Data Index: 219310 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.3267. Min Act: -0.1700
Data Index: 2926579 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.3267. Min Act: -0.1700
Data Index: 799097 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.2642. Min Act: -0.1700
Data Index: 4027307 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.3267. Min Act: -0.1700
Data Index: 6661712 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.2642. Min Act: -0.1700
Data Index: 417669 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.2955. Min Act: -0.1700
Data Index: 5654381 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.2017. Min Act: -0.1700
Data Index: 1740323 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.2642. Min Act: -0.1700
Data Index: 3648210 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.2330. Min Act: -0.1700
Data Index: 2330025 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.2330. Min Act: -0.1700
Data Index: 4916366 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.2017. Min Act: -0.1700
Data Index: 1992284 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.1392. Min Act: -0.1700
Data Index: 5312804 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.1705. Min Act: -0.1700
Data Index: 6533938 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.1392. Min Act: -0.1700
Data Index: 4485433 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.1392. Min Act: -0.1700
Data Index: 552589 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5767. Min Range: -4.5767
Max Act: 4.1392. Min Act: -0.1700
Data Index: 3342424 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #19