Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 576 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6536. Min Range: -8.6536
Max Act: 8.6536. Min Act: -0.1700
Data Index: 3966687 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6536. Min Range: -8.6536
Max Act: 8.4036. Min Act: -0.1700
Data Index: 2241703 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6536. Min Range: -8.6536
Max Act: 8.4036. Min Act: -0.1700
Data Index: 1250135 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6536. Min Range: -8.6536
Max Act: 8.3411. Min Act: -0.1700
Data Index: 2677810 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6536. Min Range: -8.6536
Max Act: 8.3411. Min Act: -0.1700
Data Index: 8464390 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6536. Min Range: -8.6536
Max Act: 8.2786. Min Act: -0.1700
Data Index: 6981455 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6536. Min Range: -8.6536
Max Act: 8.3411. Min Act: -0.1700
Data Index: 2761280 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6536. Min Range: -8.6536
Max Act: 8.2786. Min Act: -0.1700
Data Index: 8469631 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6536. Min Range: -8.6536
Max Act: 8.2161. Min Act: -0.1700
Data Index: 3874156 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6536. Min Range: -8.6536
Max Act: 8.2161. Min Act: -0.1700
Data Index: 1675850 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6536. Min Range: -8.6536
Max Act: 8.1536. Min Act: -0.1700
Data Index: 2515718 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6536. Min Range: -8.6536
Max Act: 8.1536. Min Act: -0.1700
Data Index: 1582088 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6536. Min Range: -8.6536
Max Act: 8.0911. Min Act: -0.1700
Data Index: 651635 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6536. Min Range: -8.6536
Max Act: 8.0911. Min Act: -0.1700
Data Index: 8638859 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6536. Min Range: -8.6536
Max Act: 8.1536. Min Act: -0.1700
Data Index: 3747147 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6536. Min Range: -8.6536
Max Act: 8.1536. Min Act: -0.1700
Data Index: 243449 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6536. Min Range: -8.6536
Max Act: 8.0911. Min Act: -0.1700
Data Index: 4156086 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6536. Min Range: -8.6536
Max Act: 8.0911. Min Act: -0.1700
Data Index: 1281300 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6536. Min Range: -8.6536
Max Act: 8.0599. Min Act: -0.1700
Data Index: 592212 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6536. Min Range: -8.6536
Max Act: 8.0286. Min Act: -0.1700
Data Index: 7602720 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #19