Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3815 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0833. Min Range: -6.0833
Max Act: 6.0833. Min Act: -0.1700
Data Index: 4992718 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0833. Min Range: -6.0833
Max Act: 6.0208. Min Act: -0.1700
Data Index: 1098436 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0833. Min Range: -6.0833
Max Act: 6.0208. Min Act: -0.1700
Data Index: 1579405 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0833. Min Range: -6.0833
Max Act: 5.9583. Min Act: -0.1700
Data Index: 6783908 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0833. Min Range: -6.0833
Max Act: 5.9583. Min Act: -0.1700
Data Index: 2362059 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0833. Min Range: -6.0833
Max Act: 5.8958. Min Act: -0.1700
Data Index: 4761190 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0833. Min Range: -6.0833
Max Act: 5.8646. Min Act: -0.1700
Data Index: 7751100 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0833. Min Range: -6.0833
Max Act: 5.8646. Min Act: -0.1700
Data Index: 7562891 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0833. Min Range: -6.0833
Max Act: 5.8333. Min Act: -0.1700
Data Index: 2545754 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0833. Min Range: -6.0833
Max Act: 5.8021. Min Act: -0.1700
Data Index: 62558 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0833. Min Range: -6.0833
Max Act: 5.8333. Min Act: -0.1700
Data Index: 8360367 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0833. Min Range: -6.0833
Max Act: 5.8021. Min Act: -0.1700
Data Index: 8794725 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0833. Min Range: -6.0833
Max Act: 5.8021. Min Act: -0.1700
Data Index: 642665 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0833. Min Range: -6.0833
Max Act: 5.7708. Min Act: -0.1700
Data Index: 8480584 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0833. Min Range: -6.0833
Max Act: 5.7708. Min Act: -0.1700
Data Index: 8795079 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0833. Min Range: -6.0833
Max Act: 5.7396. Min Act: -0.1700
Data Index: 3043564 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0833. Min Range: -6.0833
Max Act: 5.7396. Min Act: -0.1700
Data Index: 1662122 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0833. Min Range: -6.0833
Max Act: 5.7396. Min Act: -0.1700
Data Index: 7562897 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0833. Min Range: -6.0833
Max Act: 5.6771. Min Act: -0.1700
Data Index: 8659523 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0833. Min Range: -6.0833
Max Act: 5.7083. Min Act: -0.1700
Data Index: 2350466 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19