Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3028 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2687. Min Range: -9.2687
Max Act: 9.2687. Min Act: -0.1700
Data Index: 2429687 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2687. Min Range: -9.2687
Max Act: 7.9562. Min Act: -0.1700
Data Index: 5320870 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2687. Min Range: -9.2687
Max Act: 7.6437. Min Act: -0.1700
Data Index: 4790669 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2687. Min Range: -9.2687
Max Act: 7.5187. Min Act: -0.1700
Data Index: 7113316 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2687. Min Range: -9.2687
Max Act: 7.3937. Min Act: -0.1700
Data Index: 8501893 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2687. Min Range: -9.2687
Max Act: 7.4249. Min Act: -0.1700
Data Index: 7801125 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2687. Min Range: -9.2687
Max Act: 7.3624. Min Act: -0.1700
Data Index: 2230971 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2687. Min Range: -9.2687
Max Act: 7.3624. Min Act: -0.1700
Data Index: 7554877 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2687. Min Range: -9.2687
Max Act: 7.2999. Min Act: -0.1700
Data Index: 5424816 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2687. Min Range: -9.2687
Max Act: 7.2687. Min Act: -0.1700
Data Index: 8829566 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2687. Min Range: -9.2687
Max Act: 7.2062. Min Act: -0.1700
Data Index: 8640175 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2687. Min Range: -9.2687
Max Act: 7.2374. Min Act: -0.1700
Data Index: 3634261 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2687. Min Range: -9.2687
Max Act: 7.2062. Min Act: -0.1700
Data Index: 8188722 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2687. Min Range: -9.2687
Max Act: 7.2062. Min Act: -0.1700
Data Index: 7197712 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2687. Min Range: -9.2687
Max Act: 7.2062. Min Act: -0.1700
Data Index: 5563323 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2687. Min Range: -9.2687
Max Act: 7.2374. Min Act: -0.1700
Data Index: 6314151 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2687. Min Range: -9.2687
Max Act: 7.1749. Min Act: -0.1700
Data Index: 1177001 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2687. Min Range: -9.2687
Max Act: 7.1749. Min Act: -0.1700
Data Index: 7476986 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2687. Min Range: -9.2687
Max Act: 7.1749. Min Act: -0.1700
Data Index: 7696882 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2687. Min Range: -9.2687
Max Act: 7.1749. Min Act: -0.1700
Data Index: 5114476 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #19