Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3031 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7647. Min Range: -6.7647
Max Act: 6.7647. Min Act: -0.1700
Data Index: 7361630 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7647. Min Range: -6.7647
Max Act: 6.7335. Min Act: -0.1700
Data Index: 3258594 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7647. Min Range: -6.7647
Max Act: 6.7022. Min Act: -0.1700
Data Index: 7381057 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7647. Min Range: -6.7647
Max Act: 6.6710. Min Act: -0.1700
Data Index: 8416052 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7647. Min Range: -6.7647
Max Act: 6.6710. Min Act: -0.1700
Data Index: 8108323 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7647. Min Range: -6.7647
Max Act: 6.6710. Min Act: -0.1700
Data Index: 8194442 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7647. Min Range: -6.7647
Max Act: 6.6710. Min Act: -0.1700
Data Index: 7703601 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7647. Min Range: -6.7647
Max Act: 6.6085. Min Act: -0.1700
Data Index: 3833571 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7647. Min Range: -6.7647
Max Act: 6.6085. Min Act: -0.1700
Data Index: 3297266 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7647. Min Range: -6.7647
Max Act: 6.6085. Min Act: -0.1700
Data Index: 2086614 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7647. Min Range: -6.7647
Max Act: 6.6085. Min Act: -0.1700
Data Index: 1495157 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7647. Min Range: -6.7647
Max Act: 6.6085. Min Act: -0.1700
Data Index: 6170601 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7647. Min Range: -6.7647
Max Act: 6.6085. Min Act: -0.1700
Data Index: 5280996 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7647. Min Range: -6.7647
Max Act: 6.6085. Min Act: -0.1700
Data Index: 5103340 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7647. Min Range: -6.7647
Max Act: 6.6085. Min Act: -0.1700
Data Index: 3867689 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7647. Min Range: -6.7647
Max Act: 6.6085. Min Act: -0.1700
Data Index: 14249 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7647. Min Range: -6.7647
Max Act: 6.6397. Min Act: -0.1700
Data Index: 1302370 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7647. Min Range: -6.7647
Max Act: 6.6085. Min Act: -0.1700
Data Index: 770467 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7647. Min Range: -6.7647
Max Act: 6.6397. Min Act: -0.1700
Data Index: 2613788 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7647. Min Range: -6.7647
Max Act: 6.5772. Min Act: -0.1700
Data Index: 3535590 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19