Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5063 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3051. Min Range: -6.3051
Max Act: 6.3051. Min Act: -0.1700
Data Index: 7791369 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3051. Min Range: -6.3051
Max Act: 6.0238. Min Act: -0.1700
Data Index: 4235778 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3051. Min Range: -6.3051
Max Act: 5.9613. Min Act: -0.1700
Data Index: 7246075 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3051. Min Range: -6.3051
Max Act: 5.8676. Min Act: -0.1700
Data Index: 1395494 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3051. Min Range: -6.3051
Max Act: 5.8676. Min Act: -0.1700
Data Index: 1271627 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3051. Min Range: -6.3051
Max Act: 5.8363. Min Act: -0.1700
Data Index: 3252866 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3051. Min Range: -6.3051
Max Act: 5.8363. Min Act: -0.1700
Data Index: 1394436 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3051. Min Range: -6.3051
Max Act: 5.8051. Min Act: -0.1700
Data Index: 1217187 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3051. Min Range: -6.3051
Max Act: 5.7738. Min Act: -0.1700
Data Index: 3441085 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3051. Min Range: -6.3051
Max Act: 5.8051. Min Act: -0.1700
Data Index: 1788956 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3051. Min Range: -6.3051
Max Act: 5.7426. Min Act: -0.1700
Data Index: 727640 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3051. Min Range: -6.3051
Max Act: 5.7738. Min Act: -0.1700
Data Index: 3947715 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3051. Min Range: -6.3051
Max Act: 5.6801. Min Act: -0.1700
Data Index: 1070199 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3051. Min Range: -6.3051
Max Act: 5.6801. Min Act: -0.1700
Data Index: 7044106 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3051. Min Range: -6.3051
Max Act: 5.6488. Min Act: -0.1700
Data Index: 5346609 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3051. Min Range: -6.3051
Max Act: 5.6176. Min Act: -0.1700
Data Index: 1420500 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3051. Min Range: -6.3051
Max Act: 5.5863. Min Act: -0.1700
Data Index: 5654887 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3051. Min Range: -6.3051
Max Act: 5.5863. Min Act: -0.1700
Data Index: 5395158 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3051. Min Range: -6.3051
Max Act: 5.5863. Min Act: -0.1700
Data Index: 3358312 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3051. Min Range: -6.3051
Max Act: 5.5551. Min Act: -0.1700
Data Index: 2770743 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #19