Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3263 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6062. Min Range: -5.6062
Max Act: 5.6062. Min Act: -0.1700
Data Index: 5135619 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6062. Min Range: -5.6062
Max Act: 5.4812. Min Act: -0.1700
Data Index: 5443815 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6062. Min Range: -5.6062
Max Act: 5.4499. Min Act: -0.1700
Data Index: 2476308 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6062. Min Range: -5.6062
Max Act: 5.4499. Min Act: -0.1700
Data Index: 4945090 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6062. Min Range: -5.6062
Max Act: 5.4499. Min Act: -0.1700
Data Index: 3118342 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6062. Min Range: -5.6062
Max Act: 5.4187. Min Act: -0.1700
Data Index: 444733 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6062. Min Range: -5.6062
Max Act: 5.4187. Min Act: -0.1700
Data Index: 3084765 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6062. Min Range: -5.6062
Max Act: 5.4187. Min Act: -0.1700
Data Index: 2611442 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6062. Min Range: -5.6062
Max Act: 5.4187. Min Act: -0.1700
Data Index: 2542345 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6062. Min Range: -5.6062
Max Act: 5.4499. Min Act: -0.1700
Data Index: 6067839 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6062. Min Range: -5.6062
Max Act: 5.4187. Min Act: -0.1700
Data Index: 2264924 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6062. Min Range: -5.6062
Max Act: 5.4187. Min Act: -0.1700
Data Index: 4016470 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6062. Min Range: -5.6062
Max Act: 5.4187. Min Act: -0.1700
Data Index: 1196894 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6062. Min Range: -5.6062
Max Act: 5.4187. Min Act: -0.1700
Data Index: 2476320 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6062. Min Range: -5.6062
Max Act: 5.4187. Min Act: -0.1700
Data Index: 3887916 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6062. Min Range: -5.6062
Max Act: 5.3874. Min Act: -0.1700
Data Index: 3185929 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6062. Min Range: -5.6062
Max Act: 5.4187. Min Act: -0.1700
Data Index: 3861493 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6062. Min Range: -5.6062
Max Act: 5.3562. Min Act: -0.1700
Data Index: 6431370 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6062. Min Range: -5.6062
Max Act: 5.3562. Min Act: -0.1700
Data Index: 1872968 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6062. Min Range: -5.6062
Max Act: 5.3562. Min Act: -0.1700
Data Index: 4514802 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19