Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3554 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4894. Min Range: -4.4894
Max Act: 4.4894. Min Act: -0.1700
Data Index: 7293010 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4894. Min Range: -4.4894
Max Act: 4.4894. Min Act: -0.1700
Data Index: 532992 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4894. Min Range: -4.4894
Max Act: 4.4581. Min Act: -0.1700
Data Index: 4472649 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4894. Min Range: -4.4894
Max Act: 4.4581. Min Act: -0.1700
Data Index: 5848309 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4894. Min Range: -4.4894
Max Act: 4.3956. Min Act: -0.1700
Data Index: 3096255 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4894. Min Range: -4.4894
Max Act: 4.3331. Min Act: -0.1700
Data Index: 80779 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4894. Min Range: -4.4894
Max Act: 4.3644. Min Act: -0.1700
Data Index: 7791247 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4894. Min Range: -4.4894
Max Act: 4.3331. Min Act: -0.1700
Data Index: 6663668 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4894. Min Range: -4.4894
Max Act: 4.3331. Min Act: -0.1700
Data Index: 3038613 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4894. Min Range: -4.4894
Max Act: 4.3019. Min Act: -0.1700
Data Index: 8650156 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4894. Min Range: -4.4894
Max Act: 4.3019. Min Act: -0.1700
Data Index: 3723860 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4894. Min Range: -4.4894
Max Act: 4.3019. Min Act: -0.1700
Data Index: 5300709 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4894. Min Range: -4.4894
Max Act: 4.2706. Min Act: -0.1700
Data Index: 3850383 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4894. Min Range: -4.4894
Max Act: 4.2706. Min Act: -0.1700
Data Index: 2064325 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4894. Min Range: -4.4894
Max Act: 4.2706. Min Act: -0.1700
Data Index: 8048872 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4894. Min Range: -4.4894
Max Act: 4.2706. Min Act: -0.1700
Data Index: 4749269 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4894. Min Range: -4.4894
Max Act: 4.2706. Min Act: -0.1700
Data Index: 7442015 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4894. Min Range: -4.4894
Max Act: 4.2706. Min Act: -0.1700
Data Index: 3819863 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4894. Min Range: -4.4894
Max Act: 4.2706. Min Act: -0.1700
Data Index: 1968107 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4894. Min Range: -4.4894
Max Act: 4.2706. Min Act: -0.1700
Data Index: 7949867 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #19