Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4496 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8767. Min Range: -3.8767
Max Act: 3.8767. Min Act: -0.1700
Data Index: 7529621 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8767. Min Range: -3.8767
Max Act: 3.8141. Min Act: -0.1700
Data Index: 1200132 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8767. Min Range: -3.8767
Max Act: 3.7516. Min Act: -0.1700
Data Index: 1586032 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8767. Min Range: -3.8767
Max Act: 3.7828. Min Act: -0.1700
Data Index: 6866189 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8767. Min Range: -3.8767
Max Act: 3.7516. Min Act: -0.1700
Data Index: 219740 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8767. Min Range: -3.8767
Max Act: 3.7203. Min Act: -0.1700
Data Index: 1270101 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8767. Min Range: -3.8767
Max Act: 3.6890. Min Act: -0.1700
Data Index: 4784334 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8767. Min Range: -3.8767
Max Act: 3.6890. Min Act: -0.1700
Data Index: 162982 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8767. Min Range: -3.8767
Max Act: 3.6734. Min Act: -0.1700
Data Index: 48029 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8767. Min Range: -3.8767
Max Act: 3.6577. Min Act: -0.1700
Data Index: 8687213 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8767. Min Range: -3.8767
Max Act: 3.6421. Min Act: -0.1700
Data Index: 3452311 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8767. Min Range: -3.8767
Max Act: 3.6264. Min Act: -0.1700
Data Index: 7902614 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8767. Min Range: -3.8767
Max Act: 3.6108. Min Act: -0.1700
Data Index: 2375672 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8767. Min Range: -3.8767
Max Act: 3.5795. Min Act: -0.1700
Data Index: 844949 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8767. Min Range: -3.8767
Max Act: 3.5951. Min Act: -0.1700
Data Index: 5669394 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8767. Min Range: -3.8767
Max Act: 3.5795. Min Act: -0.1700
Data Index: 6228035 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8767. Min Range: -3.8767
Max Act: 3.5951. Min Act: -0.1700
Data Index: 7759591 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8767. Min Range: -3.8767
Max Act: 3.5795. Min Act: -0.1700
Data Index: 3674297 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8767. Min Range: -3.8767
Max Act: 3.5638. Min Act: -0.1700
Data Index: 6486404 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8767. Min Range: -3.8767
Max Act: 3.5481. Min Act: -0.1700
Data Index: 5150730 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19