Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1031 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6698. Min Range: -3.6698
Max Act: 3.6698. Min Act: -0.1700
Data Index: 1904254 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6698. Min Range: -3.6698
Max Act: 3.5446. Min Act: -0.1700
Data Index: 5877607 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6698. Min Range: -3.6698
Max Act: 3.5133. Min Act: -0.1700
Data Index: 174355 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6698. Min Range: -3.6698
Max Act: 3.5133. Min Act: -0.1700
Data Index: 8600199 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6698. Min Range: -3.6698
Max Act: 3.5133. Min Act: -0.1700
Data Index: 6623807 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6698. Min Range: -3.6698
Max Act: 3.4820. Min Act: -0.1700
Data Index: 2797357 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6698. Min Range: -3.6698
Max Act: 3.4820. Min Act: -0.1700
Data Index: 6119967 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6698. Min Range: -3.6698
Max Act: 3.4820. Min Act: -0.1700
Data Index: 5803980 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6698. Min Range: -3.6698
Max Act: 3.5133. Min Act: -0.1700
Data Index: 5775501 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6698. Min Range: -3.6698
Max Act: 3.4820. Min Act: -0.1700
Data Index: 2352340 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6698. Min Range: -3.6698
Max Act: 3.4820. Min Act: -0.1700
Data Index: 4557268 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6698. Min Range: -3.6698
Max Act: 3.4820. Min Act: -0.1700
Data Index: 8784746 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6698. Min Range: -3.6698
Max Act: 3.5133. Min Act: -0.1700
Data Index: 2847768 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6698. Min Range: -3.6698
Max Act: 3.4820. Min Act: -0.1700
Data Index: 6358891 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6698. Min Range: -3.6698
Max Act: 3.4507. Min Act: -0.1700
Data Index: 2057722 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6698. Min Range: -3.6698
Max Act: 3.4507. Min Act: -0.1700
Data Index: 5615236 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6698. Min Range: -3.6698
Max Act: 3.4820. Min Act: -0.1700
Data Index: 4489532 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6698. Min Range: -3.6698
Max Act: 3.4507. Min Act: -0.1700
Data Index: 1100146 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6698. Min Range: -3.6698
Max Act: 3.4507. Min Act: -0.1700
Data Index: 2407085 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6698. Min Range: -3.6698
Max Act: 3.4507. Min Act: -0.1700
Data Index: 1867151 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19