Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3366 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5073. Min Range: -5.5073
Max Act: 5.5073. Min Act: -0.1700
Data Index: 411786 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5073. Min Range: -5.5073
Max Act: 5.1323. Min Act: -0.1700
Data Index: 4615580 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5073. Min Range: -5.5073
Max Act: 5.0073. Min Act: -0.1700
Data Index: 6891930 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5073. Min Range: -5.5073
Max Act: 4.9761. Min Act: -0.1700
Data Index: 7812148 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5073. Min Range: -5.5073
Max Act: 4.9761. Min Act: -0.1700
Data Index: 8396891 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5073. Min Range: -5.5073
Max Act: 4.9448. Min Act: -0.1700
Data Index: 5157003 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5073. Min Range: -5.5073
Max Act: 4.9448. Min Act: -0.1700
Data Index: 1084782 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5073. Min Range: -5.5073
Max Act: 4.8823. Min Act: -0.1700
Data Index: 8712049 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5073. Min Range: -5.5073
Max Act: 4.8823. Min Act: -0.1700
Data Index: 1312114 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5073. Min Range: -5.5073
Max Act: 4.7886. Min Act: -0.1700
Data Index: 5422093 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5073. Min Range: -5.5073
Max Act: 4.8198. Min Act: -0.1700
Data Index: 5396111 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5073. Min Range: -5.5073
Max Act: 4.8198. Min Act: -0.1700
Data Index: 1715933 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5073. Min Range: -5.5073
Max Act: 4.8511. Min Act: -0.1700
Data Index: 1186621 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5073. Min Range: -5.5073
Max Act: 4.7886. Min Act: -0.1700
Data Index: 1514647 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5073. Min Range: -5.5073
Max Act: 4.7886. Min Act: -0.1700
Data Index: 5426757 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5073. Min Range: -5.5073
Max Act: 4.7886. Min Act: -0.1700
Data Index: 8516755 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5073. Min Range: -5.5073
Max Act: 4.7573. Min Act: -0.1700
Data Index: 8312246 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5073. Min Range: -5.5073
Max Act: 4.7573. Min Act: -0.1700
Data Index: 2054376 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5073. Min Range: -5.5073
Max Act: 4.7573. Min Act: -0.1700
Data Index: 6372789 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5073. Min Range: -5.5073
Max Act: 4.7573. Min Act: -0.1700
Data Index: 7945762 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19