Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2915 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.6876. Min Range: -0.6876
Max Act: 0.6876. Min Act: -0.1700
Data Index: 3562531 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6876. Min Range: -0.6876
Max Act: 0.6795. Min Act: -0.1700
Data Index: 1550021 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6876. Min Range: -0.6876
Max Act: 0.6552. Min Act: -0.1697
Data Index: 7743577 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6876. Min Range: -0.6876
Max Act: 0.6633. Min Act: -0.1695
Data Index: 7348443 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6876. Min Range: -0.6876
Max Act: 0.6472. Min Act: -0.1598
Data Index: 7432004 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6876. Min Range: -0.6876
Max Act: 0.6312. Min Act: -0.1700
Data Index: 1515922 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6876. Min Range: -0.6876
Max Act: 0.6392. Min Act: -0.1700
Data Index: 788798 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6876. Min Range: -0.6876
Max Act: 0.6472. Min Act: -0.1700
Data Index: 8649875 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6876. Min Range: -0.6876
Max Act: 0.6312. Min Act: -0.1697
Data Index: 1860841 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6876. Min Range: -0.6876
Max Act: 0.6312. Min Act: -0.1700
Data Index: 5603353 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6876. Min Range: -0.6876
Max Act: 0.6312. Min Act: -0.1545
Data Index: 180892 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6876. Min Range: -0.6876
Max Act: 0.6312. Min Act: -0.1700
Data Index: 7371490 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6876. Min Range: -0.6876
Max Act: 0.6233. Min Act: -0.1700
Data Index: 4822416 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6876. Min Range: -0.6876
Max Act: 0.6233. Min Act: -0.1696
Data Index: 6706013 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6876. Min Range: -0.6876
Max Act: 0.6233. Min Act: -0.1697
Data Index: 5027110 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6876. Min Range: -0.6876
Max Act: 0.6312. Min Act: -0.1700
Data Index: 7674102 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6876. Min Range: -0.6876
Max Act: 0.6233. Min Act: -0.1680
Data Index: 278017 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6876. Min Range: -0.6876
Max Act: 0.6233. Min Act: -0.1700
Data Index: 5524969 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6876. Min Range: -0.6876
Max Act: 0.6153. Min Act: -0.1700
Data Index: 418219 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6876. Min Range: -0.6876
Max Act: 0.6153. Min Act: -0.1699
Data Index: 564861 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19