Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 757 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7180. Min Range: -6.7180
Max Act: 6.7180. Min Act: -0.1700
Data Index: 1378630 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7180. Min Range: -6.7180
Max Act: 6.5618. Min Act: -0.1700
Data Index: 8253408 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7180. Min Range: -6.7180
Max Act: 6.3118. Min Act: -0.1700
Data Index: 2783730 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7180. Min Range: -6.7180
Max Act: 6.2180. Min Act: -0.1700
Data Index: 1030678 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7180. Min Range: -6.7180
Max Act: 6.2180. Min Act: -0.1700
Data Index: 7706238 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7180. Min Range: -6.7180
Max Act: 6.2180. Min Act: -0.1700
Data Index: 2913417 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7180. Min Range: -6.7180
Max Act: 6.2180. Min Act: -0.1700
Data Index: 4726917 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7180. Min Range: -6.7180
Max Act: 6.1868. Min Act: -0.1700
Data Index: 1053426 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7180. Min Range: -6.7180
Max Act: 6.1868. Min Act: -0.1700
Data Index: 2940779 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7180. Min Range: -6.7180
Max Act: 6.1868. Min Act: -0.1700
Data Index: 7809034 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7180. Min Range: -6.7180
Max Act: 6.1243. Min Act: -0.1700
Data Index: 7407524 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7180. Min Range: -6.7180
Max Act: 6.1243. Min Act: -0.1700
Data Index: 1775364 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7180. Min Range: -6.7180
Max Act: 6.0930. Min Act: -0.1700
Data Index: 2578286 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7180. Min Range: -6.7180
Max Act: 6.0930. Min Act: -0.1700
Data Index: 1628805 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7180. Min Range: -6.7180
Max Act: 6.0930. Min Act: -0.1700
Data Index: 6058904 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7180. Min Range: -6.7180
Max Act: 6.0930. Min Act: -0.1700
Data Index: 7680190 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7180. Min Range: -6.7180
Max Act: 6.0930. Min Act: -0.1700
Data Index: 7697871 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7180. Min Range: -6.7180
Max Act: 6.0930. Min Act: -0.1700
Data Index: 7345836 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7180. Min Range: -6.7180
Max Act: 6.0618. Min Act: -0.1700
Data Index: 5580009 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7180. Min Range: -6.7180
Max Act: 6.0618. Min Act: -0.1700
Data Index: 6100694 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19