Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3710 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8511. Min Range: -3.8511
Max Act: 3.8511. Min Act: -0.1700
Data Index: 3930191 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8511. Min Range: -3.8511
Max Act: 3.8198. Min Act: -0.1700
Data Index: 613673 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8511. Min Range: -3.8511
Max Act: 3.7885. Min Act: -0.1700
Data Index: 5001079 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8511. Min Range: -3.8511
Max Act: 3.7572. Min Act: -0.1700
Data Index: 3926722 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8511. Min Range: -3.8511
Max Act: 3.7572. Min Act: -0.1700
Data Index: 5943470 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8511. Min Range: -3.8511
Max Act: 3.7572. Min Act: -0.1700
Data Index: 251094 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8511. Min Range: -3.8511
Max Act: 3.7572. Min Act: -0.1700
Data Index: 5675683 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8511. Min Range: -3.8511
Max Act: 3.7572. Min Act: -0.1700
Data Index: 4169032 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8511. Min Range: -3.8511
Max Act: 3.7572. Min Act: -0.1700
Data Index: 2982051 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8511. Min Range: -3.8511
Max Act: 3.7260. Min Act: -0.1700
Data Index: 392916 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8511. Min Range: -3.8511
Max Act: 3.7260. Min Act: -0.1700
Data Index: 650936 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8511. Min Range: -3.8511
Max Act: 3.7260. Min Act: -0.1700
Data Index: 1282239 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8511. Min Range: -3.8511
Max Act: 3.7260. Min Act: -0.1700
Data Index: 3157907 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8511. Min Range: -3.8511
Max Act: 3.7260. Min Act: -0.1700
Data Index: 166183 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8511. Min Range: -3.8511
Max Act: 3.7260. Min Act: -0.1700
Data Index: 4790121 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8511. Min Range: -3.8511
Max Act: 3.7260. Min Act: -0.1700
Data Index: 2376259 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8511. Min Range: -3.8511
Max Act: 3.7260. Min Act: -0.1700
Data Index: 2276474 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8511. Min Range: -3.8511
Max Act: 3.7260. Min Act: -0.1700
Data Index: 5874795 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8511. Min Range: -3.8511
Max Act: 3.7260. Min Act: -0.1700
Data Index: 1826969 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8511. Min Range: -3.8511
Max Act: 3.7260. Min Act: -0.1700
Data Index: 1315479 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19