Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4475 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3298. Min Range: -4.3298
Max Act: 4.3298. Min Act: -0.1700
Data Index: 8320568 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3298. Min Range: -4.3298
Max Act: 4.3298. Min Act: -0.1700
Data Index: 4678299 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3298. Min Range: -4.3298
Max Act: 4.3298. Min Act: -0.1700
Data Index: 8368329 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3298. Min Range: -4.3298
Max Act: 4.2986. Min Act: -0.1700
Data Index: 2439800 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3298. Min Range: -4.3298
Max Act: 4.2986. Min Act: -0.1700
Data Index: 4150060 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3298. Min Range: -4.3298
Max Act: 4.2986. Min Act: -0.1700
Data Index: 5748248 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3298. Min Range: -4.3298
Max Act: 4.2986. Min Act: -0.1700
Data Index: 8553682 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3298. Min Range: -4.3298
Max Act: 4.2048. Min Act: -0.1700
Data Index: 1391698 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3298. Min Range: -4.3298
Max Act: 4.1735. Min Act: -0.1700
Data Index: 7061967 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3298. Min Range: -4.3298
Max Act: 4.1735. Min Act: -0.1700
Data Index: 4454960 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3298. Min Range: -4.3298
Max Act: 4.1110. Min Act: -0.1700
Data Index: 8792384 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3298. Min Range: -4.3298
Max Act: 4.1423. Min Act: -0.1700
Data Index: 398472 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3298. Min Range: -4.3298
Max Act: 4.1110. Min Act: -0.1700
Data Index: 6358344 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3298. Min Range: -4.3298
Max Act: 4.1110. Min Act: -0.1700
Data Index: 5488187 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3298. Min Range: -4.3298
Max Act: 4.1110. Min Act: -0.1700
Data Index: 694305 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3298. Min Range: -4.3298
Max Act: 4.1110. Min Act: -0.1700
Data Index: 1989743 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3298. Min Range: -4.3298
Max Act: 4.1110. Min Act: -0.1700
Data Index: 6358349 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3298. Min Range: -4.3298
Max Act: 4.1110. Min Act: -0.1700
Data Index: 2092763 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3298. Min Range: -4.3298
Max Act: 4.0798. Min Act: -0.1700
Data Index: 6965260 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3298. Min Range: -4.3298
Max Act: 4.0798. Min Act: -0.1700
Data Index: 5140421 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19