Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4796 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1589. Min Range: -3.1589
Max Act: 3.1589. Min Act: -0.1700
Data Index: 5079219 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1589. Min Range: -3.1589
Max Act: 3.0802. Min Act: -0.1700
Data Index: 968454 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1589. Min Range: -3.1589
Max Act: 2.9696. Min Act: -0.1700
Data Index: 1372054 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1589. Min Range: -3.1589
Max Act: 2.9696. Min Act: -0.1700
Data Index: 6974673 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1589. Min Range: -3.1589
Max Act: 2.9538. Min Act: -0.1700
Data Index: 2059170 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1589. Min Range: -3.1589
Max Act: 2.9696. Min Act: -0.1700
Data Index: 1333823 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1589. Min Range: -3.1589
Max Act: 2.9063. Min Act: -0.1700
Data Index: 2393858 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1589. Min Range: -3.1589
Max Act: 2.9063. Min Act: -0.1700
Data Index: 6681071 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1589. Min Range: -3.1589
Max Act: 2.9063. Min Act: -0.1700
Data Index: 5563047 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1589. Min Range: -3.1589
Max Act: 2.8587. Min Act: -0.1700
Data Index: 5887911 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1589. Min Range: -3.1589
Max Act: 2.8428. Min Act: -0.1700
Data Index: 6938348 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1589. Min Range: -3.1589
Max Act: 2.8428. Min Act: -0.1700
Data Index: 6561417 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1589. Min Range: -3.1589
Max Act: 2.8428. Min Act: -0.1700
Data Index: 3742421 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1589. Min Range: -3.1589
Max Act: 2.8428. Min Act: -0.1700
Data Index: 2146258 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1589. Min Range: -3.1589
Max Act: 2.8269. Min Act: -0.1700
Data Index: 2339577 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1589. Min Range: -3.1589
Max Act: 2.8110. Min Act: -0.1700
Data Index: 195687 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1589. Min Range: -3.1589
Max Act: 2.8110. Min Act: -0.1700
Data Index: 7310144 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1589. Min Range: -3.1589
Max Act: 2.8110. Min Act: -0.1700
Data Index: 6594901 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1589. Min Range: -3.1589
Max Act: 2.8110. Min Act: -0.1700
Data Index: 1512250 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1589. Min Range: -3.1589
Max Act: 2.7951. Min Act: -0.1700
Data Index: 3248661 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19