Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4001 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0556. Min Range: -6.0556
Max Act: 6.0556. Min Act: -0.1700
Data Index: 5724349 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0556. Min Range: -6.0556
Max Act: 5.9931. Min Act: -0.1700
Data Index: 6521756 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0556. Min Range: -6.0556
Max Act: 5.9931. Min Act: -0.1700
Data Index: 2898419 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0556. Min Range: -6.0556
Max Act: 5.9306. Min Act: -0.1700
Data Index: 8209683 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0556. Min Range: -6.0556
Max Act: 5.8681. Min Act: -0.1700
Data Index: 8576058 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0556. Min Range: -6.0556
Max Act: 5.8056. Min Act: -0.1700
Data Index: 5050421 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0556. Min Range: -6.0556
Max Act: 5.8056. Min Act: -0.1700
Data Index: 2441500 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0556. Min Range: -6.0556
Max Act: 5.8056. Min Act: -0.1700
Data Index: 430445 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0556. Min Range: -6.0556
Max Act: 5.8056. Min Act: -0.1700
Data Index: 5835906 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0556. Min Range: -6.0556
Max Act: 5.7744. Min Act: -0.1700
Data Index: 5747301 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0556. Min Range: -6.0556
Max Act: 5.7744. Min Act: -0.1700
Data Index: 6099808 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0556. Min Range: -6.0556
Max Act: 5.7744. Min Act: -0.1700
Data Index: 5724348 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0556. Min Range: -6.0556
Max Act: 5.7431. Min Act: -0.1700
Data Index: 3598217 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0556. Min Range: -6.0556
Max Act: 5.7431. Min Act: -0.1700
Data Index: 7568920 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0556. Min Range: -6.0556
Max Act: 5.7431. Min Act: -0.1700
Data Index: 6244917 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0556. Min Range: -6.0556
Max Act: 5.7119. Min Act: -0.1700
Data Index: 3151241 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0556. Min Range: -6.0556
Max Act: 5.7119. Min Act: -0.1700
Data Index: 5768766 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0556. Min Range: -6.0556
Max Act: 5.7119. Min Act: -0.1700
Data Index: 7018489 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0556. Min Range: -6.0556
Max Act: 5.6806. Min Act: -0.1700
Data Index: 3761014 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0556. Min Range: -6.0556
Max Act: 5.6494. Min Act: -0.1700
Data Index: 6617806 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19