Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 753 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.3814. Min Act: -0.1700
Data Index: 6091733 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.3501. Min Act: -0.1700
Data Index: 6616574 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.3344. Min Act: -0.1700
Data Index: 5272194 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.3187. Min Act: -0.1700
Data Index: 8054089 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.3187. Min Act: -0.1700
Data Index: 5353546 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.3030. Min Act: -0.1700
Data Index: 5290884 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.3030. Min Act: -0.1700
Data Index: 7757417 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.2873. Min Act: -0.1700
Data Index: 6586961 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.3187. Min Act: -0.1700
Data Index: 7805771 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.3187. Min Act: -0.1700
Data Index: 7041728 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.2873. Min Act: -0.1700
Data Index: 4841667 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.2873. Min Act: -0.1700
Data Index: 799276 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.2873. Min Act: -0.1700
Data Index: 2899745 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.2873. Min Act: -0.1700
Data Index: 8556996 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.2716. Min Act: -0.1700
Data Index: 844302 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.2559. Min Act: -0.1700
Data Index: 3127574 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.2402. Min Act: -0.1700
Data Index: 8159498 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.2402. Min Act: -0.1700
Data Index: 1246799 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.2559. Min Act: -0.1700
Data Index: 6911622 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3814. Min Range: -3.3814
Max Act: 3.2559. Min Act: -0.1700
Data Index: 7566778 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19