Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2812 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.8583. Min Act: -0.1700
Data Index: 861900 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.7333. Min Act: -0.1700
Data Index: 2604743 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.6708. Min Act: -0.1700
Data Index: 2323813 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.6396. Min Act: -0.1700
Data Index: 1483385 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.6083. Min Act: -0.1700
Data Index: 491258 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.5458. Min Act: -0.1700
Data Index: 3715372 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.5146. Min Act: -0.1700
Data Index: 5137267 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.5771. Min Act: -0.1700
Data Index: 600681 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.5458. Min Act: -0.1700
Data Index: 1380340 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.5146. Min Act: -0.1700
Data Index: 4608309 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.5146. Min Act: -0.1700
Data Index: 771717 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.5146. Min Act: -0.1700
Data Index: 6744543 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.5146. Min Act: -0.1700
Data Index: 307718 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.5146. Min Act: -0.1700
Data Index: 7744033 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.5146. Min Act: -0.1700
Data Index: 2000751 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.5146. Min Act: -0.1700
Data Index: 29764 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.5146. Min Act: -0.1700
Data Index: 6256702 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.4833. Min Act: -0.1700
Data Index: 3209040 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.4833. Min Act: -0.1700
Data Index: 6605449 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8583. Min Range: -4.8583
Max Act: 4.4833. Min Act: -0.1700
Data Index: 6854610 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #19