Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3615 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2080. Min Range: -5.2080
Max Act: 5.2080. Min Act: -0.1700
Data Index: 1289477 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2080. Min Range: -5.2080
Max Act: 5.0518. Min Act: -0.1700
Data Index: 5485631 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2080. Min Range: -5.2080
Max Act: 5.0205. Min Act: -0.1700
Data Index: 936184 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2080. Min Range: -5.2080
Max Act: 4.9580. Min Act: -0.1700
Data Index: 5401673 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2080. Min Range: -5.2080
Max Act: 4.9268. Min Act: -0.1700
Data Index: 5362957 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2080. Min Range: -5.2080
Max Act: 4.8955. Min Act: -0.1700
Data Index: 507684 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2080. Min Range: -5.2080
Max Act: 4.8643. Min Act: -0.1700
Data Index: 2202847 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2080. Min Range: -5.2080
Max Act: 4.8330. Min Act: -0.1700
Data Index: 6128793 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2080. Min Range: -5.2080
Max Act: 4.8018. Min Act: -0.1700
Data Index: 126817 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2080. Min Range: -5.2080
Max Act: 4.8330. Min Act: -0.1700
Data Index: 6614748 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2080. Min Range: -5.2080
Max Act: 4.7705. Min Act: -0.1700
Data Index: 4043070 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2080. Min Range: -5.2080
Max Act: 4.8018. Min Act: -0.1700
Data Index: 7219860 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2080. Min Range: -5.2080
Max Act: 4.7705. Min Act: -0.1700
Data Index: 2614044 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2080. Min Range: -5.2080
Max Act: 4.7705. Min Act: -0.1700
Data Index: 8106369 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2080. Min Range: -5.2080
Max Act: 4.7393. Min Act: -0.1700
Data Index: 8479697 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2080. Min Range: -5.2080
Max Act: 4.7393. Min Act: -0.1700
Data Index: 4758254 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2080. Min Range: -5.2080
Max Act: 4.7393. Min Act: -0.1700
Data Index: 6240815 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2080. Min Range: -5.2080
Max Act: 4.7393. Min Act: -0.1700
Data Index: 7029211 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2080. Min Range: -5.2080
Max Act: 4.7393. Min Act: -0.1700
Data Index: 3510802 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2080. Min Range: -5.2080
Max Act: 4.7393. Min Act: -0.1700
Data Index: 2772558 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19