Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2772 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9691. Min Range: -5.9691
Max Act: 5.9691. Min Act: -0.1700
Data Index: 4273204 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9691. Min Range: -5.9691
Max Act: 5.9379. Min Act: -0.1700
Data Index: 61160 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9691. Min Range: -5.9691
Max Act: 5.9066. Min Act: -0.1700
Data Index: 2621775 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9691. Min Range: -5.9691
Max Act: 5.8754. Min Act: -0.1700
Data Index: 2873145 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9691. Min Range: -5.9691
Max Act: 5.8754. Min Act: -0.1700
Data Index: 4019946 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9691. Min Range: -5.9691
Max Act: 5.9066. Min Act: -0.1700
Data Index: 1294117 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9691. Min Range: -5.9691
Max Act: 5.8754. Min Act: -0.1700
Data Index: 1303327 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9691. Min Range: -5.9691
Max Act: 5.8754. Min Act: -0.1700
Data Index: 862078 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9691. Min Range: -5.9691
Max Act: 5.8129. Min Act: -0.1700
Data Index: 3179208 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9691. Min Range: -5.9691
Max Act: 5.8441. Min Act: -0.1700
Data Index: 7840668 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9691. Min Range: -5.9691
Max Act: 5.8441. Min Act: -0.1700
Data Index: 5031935 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9691. Min Range: -5.9691
Max Act: 5.7816. Min Act: -0.1700
Data Index: 8024258 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9691. Min Range: -5.9691
Max Act: 5.7816. Min Act: -0.1700
Data Index: 5398079 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9691. Min Range: -5.9691
Max Act: 5.7504. Min Act: -0.1700
Data Index: 7781925 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9691. Min Range: -5.9691
Max Act: 5.7504. Min Act: -0.1700
Data Index: 833961 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9691. Min Range: -5.9691
Max Act: 5.7191. Min Act: -0.1700
Data Index: 3380375 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9691. Min Range: -5.9691
Max Act: 5.6879. Min Act: -0.1700
Data Index: 7763082 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9691. Min Range: -5.9691
Max Act: 5.7504. Min Act: -0.1700
Data Index: 4362209 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9691. Min Range: -5.9691
Max Act: 5.7504. Min Act: -0.1700
Data Index: 6050520 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9691. Min Range: -5.9691
Max Act: 5.7191. Min Act: -0.1700
Data Index: 7867874 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19