Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5772 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9715. Min Range: -6.9715
Max Act: 6.9715. Min Act: -0.1700
Data Index: 3866030 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9715. Min Range: -6.9715
Max Act: 6.5653. Min Act: -0.1700
Data Index: 3899547 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9715. Min Range: -6.9715
Max Act: 6.3153. Min Act: -0.1700
Data Index: 596726 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9715. Min Range: -6.9715
Max Act: 6.3153. Min Act: -0.1700
Data Index: 5446460 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9715. Min Range: -6.9715
Max Act: 6.2215. Min Act: -0.1700
Data Index: 5652812 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9715. Min Range: -6.9715
Max Act: 6.2528. Min Act: -0.1700
Data Index: 3789517 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9715. Min Range: -6.9715
Max Act: 6.2528. Min Act: -0.1700
Data Index: 6824582 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9715. Min Range: -6.9715
Max Act: 6.1590. Min Act: -0.1700
Data Index: 5586042 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9715. Min Range: -6.9715
Max Act: 6.0965. Min Act: -0.1700
Data Index: 2962633 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9715. Min Range: -6.9715
Max Act: 6.0340. Min Act: -0.1700
Data Index: 46208 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9715. Min Range: -6.9715
Max Act: 6.0028. Min Act: -0.1700
Data Index: 5359404 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9715. Min Range: -6.9715
Max Act: 5.9715. Min Act: -0.1700
Data Index: 2464154 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9715. Min Range: -6.9715
Max Act: 5.9403. Min Act: -0.1700
Data Index: 8812203 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9715. Min Range: -6.9715
Max Act: 5.9403. Min Act: -0.1700
Data Index: 8068168 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9715. Min Range: -6.9715
Max Act: 5.9715. Min Act: -0.1700
Data Index: 5669765 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9715. Min Range: -6.9715
Max Act: 5.9403. Min Act: -0.1700
Data Index: 4893460 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9715. Min Range: -6.9715
Max Act: 5.9403. Min Act: -0.1700
Data Index: 5430792 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9715. Min Range: -6.9715
Max Act: 5.8778. Min Act: -0.1700
Data Index: 2366079 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9715. Min Range: -6.9715
Max Act: 5.8778. Min Act: -0.1700
Data Index: 7425272 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9715. Min Range: -6.9715
Max Act: 5.9090. Min Act: -0.1700
Data Index: 3166360 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #19