Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5811 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9476. Min Range: -6.9476
Max Act: 6.9476. Min Act: -0.1700
Data Index: 945954 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9476. Min Range: -6.9476
Max Act: 6.6039. Min Act: -0.1700
Data Index: 1922387 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9476. Min Range: -6.9476
Max Act: 6.6039. Min Act: -0.1700
Data Index: 4522686 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9476. Min Range: -6.9476
Max Act: 6.6039. Min Act: -0.1700
Data Index: 3043896 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9476. Min Range: -6.9476
Max Act: 6.5101. Min Act: -0.1700
Data Index: 2888750 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9476. Min Range: -6.9476
Max Act: 6.4789. Min Act: -0.1700
Data Index: 7833595 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9476. Min Range: -6.9476
Max Act: 6.4476. Min Act: -0.1700
Data Index: 7282642 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9476. Min Range: -6.9476
Max Act: 6.4476. Min Act: -0.1700
Data Index: 2756602 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9476. Min Range: -6.9476
Max Act: 6.4476. Min Act: -0.1700
Data Index: 2481293 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9476. Min Range: -6.9476
Max Act: 6.4164. Min Act: -0.1700
Data Index: 960989 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9476. Min Range: -6.9476
Max Act: 6.4476. Min Act: -0.1700
Data Index: 1189935 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9476. Min Range: -6.9476
Max Act: 6.4476. Min Act: -0.1700
Data Index: 758617 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9476. Min Range: -6.9476
Max Act: 6.4476. Min Act: -0.1700
Data Index: 3295120 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9476. Min Range: -6.9476
Max Act: 6.4164. Min Act: -0.1700
Data Index: 944846 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9476. Min Range: -6.9476
Max Act: 6.3539. Min Act: -0.1700
Data Index: 1850682 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9476. Min Range: -6.9476
Max Act: 6.3851. Min Act: -0.1700
Data Index: 4621855 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9476. Min Range: -6.9476
Max Act: 6.3851. Min Act: -0.1700
Data Index: 3635050 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9476. Min Range: -6.9476
Max Act: 6.3539. Min Act: -0.1700
Data Index: 7439289 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9476. Min Range: -6.9476
Max Act: 6.3539. Min Act: -0.1700
Data Index: 3290509 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9476. Min Range: -6.9476
Max Act: 6.3539. Min Act: -0.1700
Data Index: 1983654 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19