Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3866 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1051. Min Range: -5.1051
Max Act: 5.1051. Min Act: -0.1700
Data Index: 3060990 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1051. Min Range: -5.1051
Max Act: 5.1051. Min Act: -0.1700
Data Index: 8128654 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1051. Min Range: -5.1051
Max Act: 4.9801. Min Act: -0.1700
Data Index: 8193661 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1051. Min Range: -5.1051
Max Act: 4.9801. Min Act: -0.1700
Data Index: 4833539 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1051. Min Range: -5.1051
Max Act: 4.9801. Min Act: -0.1700
Data Index: 3285218 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1051. Min Range: -5.1051
Max Act: 4.9489. Min Act: -0.1700
Data Index: 2917004 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1051. Min Range: -5.1051
Max Act: 4.9176. Min Act: -0.1700
Data Index: 8733797 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1051. Min Range: -5.1051
Max Act: 4.9801. Min Act: -0.1700
Data Index: 1790331 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1051. Min Range: -5.1051
Max Act: 4.9489. Min Act: -0.1700
Data Index: 3060989 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1051. Min Range: -5.1051
Max Act: 4.9489. Min Act: -0.1700
Data Index: 871618 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1051. Min Range: -5.1051
Max Act: 4.9176. Min Act: -0.1700
Data Index: 742097 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1051. Min Range: -5.1051
Max Act: 4.9176. Min Act: -0.1700
Data Index: 1682095 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1051. Min Range: -5.1051
Max Act: 4.9176. Min Act: -0.1700
Data Index: 8117650 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1051. Min Range: -5.1051
Max Act: 4.9489. Min Act: -0.1700
Data Index: 836004 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1051. Min Range: -5.1051
Max Act: 4.8864. Min Act: -0.1700
Data Index: 655862 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1051. Min Range: -5.1051
Max Act: 4.8864. Min Act: -0.1700
Data Index: 7391047 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1051. Min Range: -5.1051
Max Act: 4.8551. Min Act: -0.1700
Data Index: 8668388 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1051. Min Range: -5.1051
Max Act: 4.8551. Min Act: -0.1700
Data Index: 5179231 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1051. Min Range: -5.1051
Max Act: 4.8551. Min Act: -0.1700
Data Index: 5616882 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1051. Min Range: -5.1051
Max Act: 4.8239. Min Act: -0.1700
Data Index: 1265973 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #19