Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4664 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0263. Min Range: -8.0263
Max Act: 8.0263. Min Act: -0.1700
Data Index: 1612732 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0263. Min Range: -8.0263
Max Act: 7.5263. Min Act: -0.1700
Data Index: 3386907 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0263. Min Range: -8.0263
Max Act: 7.4638. Min Act: -0.1700
Data Index: 5638352 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0263. Min Range: -8.0263
Max Act: 7.4638. Min Act: -0.1700
Data Index: 388768 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0263. Min Range: -8.0263
Max Act: 7.3388. Min Act: -0.1700
Data Index: 3813997 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0263. Min Range: -8.0263
Max Act: 7.3076. Min Act: -0.1700
Data Index: 6886977 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0263. Min Range: -8.0263
Max Act: 7.3076. Min Act: -0.1700
Data Index: 6310514 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0263. Min Range: -8.0263
Max Act: 7.3076. Min Act: -0.1700
Data Index: 800532 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0263. Min Range: -8.0263
Max Act: 7.1201. Min Act: -0.1700
Data Index: 1067207 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0263. Min Range: -8.0263
Max Act: 7.1201. Min Act: -0.1700
Data Index: 5870746 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0263. Min Range: -8.0263
Max Act: 7.0888. Min Act: -0.1700
Data Index: 3812697 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0263. Min Range: -8.0263
Max Act: 7.0576. Min Act: -0.1700
Data Index: 4085519 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0263. Min Range: -8.0263
Max Act: 7.0576. Min Act: -0.1700
Data Index: 1721832 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0263. Min Range: -8.0263
Max Act: 7.0576. Min Act: -0.1700
Data Index: 6577639 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0263. Min Range: -8.0263
Max Act: 7.0576. Min Act: -0.1700
Data Index: 8469152 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0263. Min Range: -8.0263
Max Act: 7.0576. Min Act: -0.1700
Data Index: 1487713 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0263. Min Range: -8.0263
Max Act: 6.9951. Min Act: -0.1700
Data Index: 715094 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0263. Min Range: -8.0263
Max Act: 6.9951. Min Act: -0.1700
Data Index: 6440889 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0263. Min Range: -8.0263
Max Act: 6.9951. Min Act: -0.1700
Data Index: 6255978 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0263. Min Range: -8.0263
Max Act: 6.9951. Min Act: -0.1700
Data Index: 3684747 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19