Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1996 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1449. Min Range: -6.1449
Max Act: 6.1449. Min Act: -0.1700
Data Index: 7250548 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1449. Min Range: -6.1449
Max Act: 6.1449. Min Act: -0.1700
Data Index: 7098875 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1449. Min Range: -6.1449
Max Act: 6.1449. Min Act: -0.1700
Data Index: 6344777 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1449. Min Range: -6.1449
Max Act: 6.0824. Min Act: -0.1700
Data Index: 1138934 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1449. Min Range: -6.1449
Max Act: 6.1137. Min Act: -0.1700
Data Index: 3306639 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1449. Min Range: -6.1449
Max Act: 6.0824. Min Act: -0.1700
Data Index: 4568817 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1449. Min Range: -6.1449
Max Act: 6.0824. Min Act: -0.1700
Data Index: 3685582 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1449. Min Range: -6.1449
Max Act: 6.0824. Min Act: -0.1700
Data Index: 6746892 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1449. Min Range: -6.1449
Max Act: 6.0512. Min Act: -0.1700
Data Index: 6146774 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1449. Min Range: -6.1449
Max Act: 6.0824. Min Act: -0.1700
Data Index: 3895124 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1449. Min Range: -6.1449
Max Act: 6.0512. Min Act: -0.1700
Data Index: 3580453 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1449. Min Range: -6.1449
Max Act: 5.9887. Min Act: -0.1700
Data Index: 1108485 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1449. Min Range: -6.1449
Max Act: 6.0199. Min Act: -0.1700
Data Index: 5823281 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1449. Min Range: -6.1449
Max Act: 6.0199. Min Act: -0.1700
Data Index: 2464448 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1449. Min Range: -6.1449
Max Act: 5.9887. Min Act: -0.1700
Data Index: 6090407 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1449. Min Range: -6.1449
Max Act: 5.9887. Min Act: -0.1700
Data Index: 4744788 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1449. Min Range: -6.1449
Max Act: 5.9887. Min Act: -0.1700
Data Index: 4370944 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1449. Min Range: -6.1449
Max Act: 5.9574. Min Act: -0.1700
Data Index: 6399494 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1449. Min Range: -6.1449
Max Act: 5.9574. Min Act: -0.1700
Data Index: 653874 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1449. Min Range: -6.1449
Max Act: 5.9574. Min Act: -0.1700
Data Index: 1667635 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #19