Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2803 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8735. Min Range: -2.8735
Max Act: 2.8735. Min Act: -0.1700
Data Index: 7013308 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8735. Min Range: -2.8735
Max Act: 2.8576. Min Act: -0.1700
Data Index: 6744087 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8735. Min Range: -2.8735
Max Act: 2.8417. Min Act: -0.1700
Data Index: 4897023 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8735. Min Range: -2.8735
Max Act: 2.8099. Min Act: -0.1700
Data Index: 3509330 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8735. Min Range: -2.8735
Max Act: 2.7781. Min Act: -0.1700
Data Index: 8762787 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8735. Min Range: -2.8735
Max Act: 2.7781. Min Act: -0.1700
Data Index: 477344 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8735. Min Range: -2.8735
Max Act: 2.7781. Min Act: -0.1700
Data Index: 7374077 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8735. Min Range: -2.8735
Max Act: 2.7781. Min Act: -0.1700
Data Index: 8706144 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8735. Min Range: -2.8735
Max Act: 2.7781. Min Act: -0.1700
Data Index: 3037790 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8735. Min Range: -2.8735
Max Act: 2.7940. Min Act: -0.1700
Data Index: 4429704 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8735. Min Range: -2.8735
Max Act: 2.7621. Min Act: -0.1700
Data Index: 8208868 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8735. Min Range: -2.8735
Max Act: 2.7462. Min Act: -0.1700
Data Index: 636157 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8735. Min Range: -2.8735
Max Act: 2.7302. Min Act: -0.1700
Data Index: 2982864 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8735. Min Range: -2.8735
Max Act: 2.7462. Min Act: -0.1700
Data Index: 7126633 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8735. Min Range: -2.8735
Max Act: 2.7462. Min Act: -0.1700
Data Index: 4115735 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8735. Min Range: -2.8735
Max Act: 2.7462. Min Act: -0.1700
Data Index: 8126654 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8735. Min Range: -2.8735
Max Act: 2.7302. Min Act: -0.1700
Data Index: 1570063 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8735. Min Range: -2.8735
Max Act: 2.7142. Min Act: -0.1700
Data Index: 7599105 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8735. Min Range: -2.8735
Max Act: 2.7302. Min Act: -0.1700
Data Index: 5561208 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8735. Min Range: -2.8735
Max Act: 2.7302. Min Act: -0.1700
Data Index: 2517993 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19