Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3081 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4666. Min Range: -7.4666
Max Act: 7.4666. Min Act: -0.1700
Data Index: 224082 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4666. Min Range: -7.4666
Max Act: 7.4354. Min Act: -0.1700
Data Index: 1186139 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4666. Min Range: -7.4666
Max Act: 7.3416. Min Act: -0.1700
Data Index: 3554149 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4666. Min Range: -7.4666
Max Act: 7.1541. Min Act: -0.1700
Data Index: 6896318 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4666. Min Range: -7.4666
Max Act: 7.1541. Min Act: -0.1700
Data Index: 6260181 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4666. Min Range: -7.4666
Max Act: 7.0916. Min Act: -0.1700
Data Index: 3738042 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4666. Min Range: -7.4666
Max Act: 7.0604. Min Act: -0.1700
Data Index: 8259841 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4666. Min Range: -7.4666
Max Act: 7.0604. Min Act: -0.1700
Data Index: 1239062 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4666. Min Range: -7.4666
Max Act: 6.9979. Min Act: -0.1700
Data Index: 5066004 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4666. Min Range: -7.4666
Max Act: 6.9666. Min Act: -0.1700
Data Index: 6252359 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4666. Min Range: -7.4666
Max Act: 6.9354. Min Act: -0.1700
Data Index: 4803313 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4666. Min Range: -7.4666
Max Act: 6.9354. Min Act: -0.1700
Data Index: 2713625 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4666. Min Range: -7.4666
Max Act: 6.9354. Min Act: -0.1700
Data Index: 1292601 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4666. Min Range: -7.4666
Max Act: 6.9354. Min Act: -0.1700
Data Index: 1181860 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4666. Min Range: -7.4666
Max Act: 6.8729. Min Act: -0.1700
Data Index: 8784931 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4666. Min Range: -7.4666
Max Act: 6.8729. Min Act: -0.1700
Data Index: 7918428 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4666. Min Range: -7.4666
Max Act: 6.8104. Min Act: -0.1700
Data Index: 6569060 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4666. Min Range: -7.4666
Max Act: 6.8416. Min Act: -0.1700
Data Index: 725517 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4666. Min Range: -7.4666
Max Act: 6.8104. Min Act: -0.1700
Data Index: 4395542 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4666. Min Range: -7.4666
Max Act: 6.7479. Min Act: -0.1700
Data Index: 3230264 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19