Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1562 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4579. Min Range: -5.4579
Max Act: 5.4579. Min Act: -0.1700
Data Index: 5927738 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4579. Min Range: -5.4579
Max Act: 5.3954. Min Act: -0.1700
Data Index: 7376749 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4579. Min Range: -5.4579
Max Act: 5.3954. Min Act: -0.1700
Data Index: 8280343 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4579. Min Range: -5.4579
Max Act: 5.3016. Min Act: -0.1700
Data Index: 8350026 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4579. Min Range: -5.4579
Max Act: 5.1766. Min Act: -0.1700
Data Index: 1298267 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4579. Min Range: -5.4579
Max Act: 5.1766. Min Act: -0.1700
Data Index: 3175078 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4579. Min Range: -5.4579
Max Act: 5.1766. Min Act: -0.1700
Data Index: 6106299 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4579. Min Range: -5.4579
Max Act: 5.1454. Min Act: -0.1700
Data Index: 4762966 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4579. Min Range: -5.4579
Max Act: 5.1454. Min Act: -0.1700
Data Index: 7160258 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4579. Min Range: -5.4579
Max Act: 5.1141. Min Act: -0.1700
Data Index: 2380914 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4579. Min Range: -5.4579
Max Act: 5.1141. Min Act: -0.1700
Data Index: 746841 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4579. Min Range: -5.4579
Max Act: 5.0829. Min Act: -0.1700
Data Index: 6009342 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4579. Min Range: -5.4579
Max Act: 5.0829. Min Act: -0.1700
Data Index: 3940277 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4579. Min Range: -5.4579
Max Act: 5.0516. Min Act: -0.1700
Data Index: 5677378 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4579. Min Range: -5.4579
Max Act: 5.0516. Min Act: -0.1700
Data Index: 8517997 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4579. Min Range: -5.4579
Max Act: 5.0516. Min Act: -0.1700
Data Index: 8657653 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4579. Min Range: -5.4579
Max Act: 5.0516. Min Act: -0.1700
Data Index: 3689766 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4579. Min Range: -5.4579
Max Act: 5.0204. Min Act: -0.1700
Data Index: 831416 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4579. Min Range: -5.4579
Max Act: 5.0204. Min Act: -0.1700
Data Index: 7843344 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4579. Min Range: -5.4579
Max Act: 5.0204. Min Act: -0.1700
Data Index: 5502854 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #19