Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 422 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2764. Min Range: -5.2764
Max Act: 5.2764. Min Act: -0.1700
Data Index: 5863019 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2764. Min Range: -5.2764
Max Act: 5.1827. Min Act: -0.1700
Data Index: 4576319 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2764. Min Range: -5.2764
Max Act: 5.2139. Min Act: -0.1700
Data Index: 1850314 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2764. Min Range: -5.2764
Max Act: 5.1827. Min Act: -0.1700
Data Index: 825027 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2764. Min Range: -5.2764
Max Act: 5.1827. Min Act: -0.1700
Data Index: 8603284 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2764. Min Range: -5.2764
Max Act: 5.1202. Min Act: -0.1700
Data Index: 6632766 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2764. Min Range: -5.2764
Max Act: 5.0889. Min Act: -0.1700
Data Index: 7472558 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2764. Min Range: -5.2764
Max Act: 5.1202. Min Act: -0.1700
Data Index: 7083462 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2764. Min Range: -5.2764
Max Act: 5.0889. Min Act: -0.1700
Data Index: 4370212 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2764. Min Range: -5.2764
Max Act: 5.0889. Min Act: -0.1700
Data Index: 8069570 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2764. Min Range: -5.2764
Max Act: 5.0577. Min Act: -0.1700
Data Index: 5795866 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2764. Min Range: -5.2764
Max Act: 5.0577. Min Act: -0.1700
Data Index: 1586099 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2764. Min Range: -5.2764
Max Act: 5.0577. Min Act: -0.1700
Data Index: 5126738 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2764. Min Range: -5.2764
Max Act: 4.9952. Min Act: -0.1700
Data Index: 6632764 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2764. Min Range: -5.2764
Max Act: 4.9952. Min Act: -0.1700
Data Index: 158110 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2764. Min Range: -5.2764
Max Act: 4.9952. Min Act: -0.1700
Data Index: 4297366 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2764. Min Range: -5.2764
Max Act: 4.9639. Min Act: -0.1700
Data Index: 5713826 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2764. Min Range: -5.2764
Max Act: 4.9639. Min Act: -0.1700
Data Index: 7109227 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2764. Min Range: -5.2764
Max Act: 4.9639. Min Act: -0.1700
Data Index: 1483264 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2764. Min Range: -5.2764
Max Act: 4.9639. Min Act: -0.1700
Data Index: 7357666 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #19