Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1007 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9651. Min Range: -8.9651
Max Act: 8.9651. Min Act: -0.1700
Data Index: 7979357 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9651. Min Range: -8.9651
Max Act: 8.7776. Min Act: -0.1700
Data Index: 2900802 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9651. Min Range: -8.9651
Max Act: 8.6526. Min Act: -0.1700
Data Index: 4523550 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9651. Min Range: -8.9651
Max Act: 8.5276. Min Act: -0.1700
Data Index: 8322561 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9651. Min Range: -8.9651
Max Act: 8.3401. Min Act: -0.1700
Data Index: 4659865 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9651. Min Range: -8.9651
Max Act: 8.3401. Min Act: -0.1700
Data Index: 6716327 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9651. Min Range: -8.9651
Max Act: 8.3401. Min Act: -0.1700
Data Index: 3837320 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9651. Min Range: -8.9651
Max Act: 8.2776. Min Act: -0.1700
Data Index: 2758261 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9651. Min Range: -8.9651
Max Act: 8.1526. Min Act: -0.1700
Data Index: 2121815 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9651. Min Range: -8.9651
Max Act: 8.1526. Min Act: -0.1700
Data Index: 7478668 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9651. Min Range: -8.9651
Max Act: 8.0901. Min Act: -0.1700
Data Index: 1642051 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9651. Min Range: -8.9651
Max Act: 8.0901. Min Act: -0.1700
Data Index: 7554861 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9651. Min Range: -8.9651
Max Act: 8.0276. Min Act: -0.1700
Data Index: 4701530 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9651. Min Range: -8.9651
Max Act: 8.0276. Min Act: -0.1700
Data Index: 6698884 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9651. Min Range: -8.9651
Max Act: 8.0276. Min Act: -0.1700
Data Index: 1793170 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9651. Min Range: -8.9651
Max Act: 8.0276. Min Act: -0.1700
Data Index: 1404633 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9651. Min Range: -8.9651
Max Act: 8.0276. Min Act: -0.1700
Data Index: 2891124 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9651. Min Range: -8.9651
Max Act: 7.9651. Min Act: -0.1700
Data Index: 5862484 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9651. Min Range: -8.9651
Max Act: 7.9651. Min Act: -0.1700
Data Index: 2293917 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9651. Min Range: -8.9651
Max Act: 7.9651. Min Act: -0.1700
Data Index: 12672 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19