Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2874 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3734. Min Range: -5.3734
Max Act: 5.3734. Min Act: -0.1700
Data Index: 553743 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3734. Min Range: -5.3734
Max Act: 5.3109. Min Act: -0.1700
Data Index: 6209546 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3734. Min Range: -5.3734
Max Act: 5.2172. Min Act: -0.1700
Data Index: 5290547 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3734. Min Range: -5.3734
Max Act: 5.2172. Min Act: -0.1700
Data Index: 4055528 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3734. Min Range: -5.3734
Max Act: 5.0922. Min Act: -0.1700
Data Index: 6330934 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3734. Min Range: -5.3734
Max Act: 5.0922. Min Act: -0.1700
Data Index: 6503363 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3734. Min Range: -5.3734
Max Act: 5.0609. Min Act: -0.1700
Data Index: 3498779 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3734. Min Range: -5.3734
Max Act: 5.0297. Min Act: -0.1700
Data Index: 277606 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3734. Min Range: -5.3734
Max Act: 5.0297. Min Act: -0.1700
Data Index: 8666355 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3734. Min Range: -5.3734
Max Act: 4.9984. Min Act: -0.1700
Data Index: 6021133 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3734. Min Range: -5.3734
Max Act: 4.9984. Min Act: -0.1700
Data Index: 3078977 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3734. Min Range: -5.3734
Max Act: 4.9984. Min Act: -0.1700
Data Index: 714171 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3734. Min Range: -5.3734
Max Act: 4.9672. Min Act: -0.1700
Data Index: 4215452 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3734. Min Range: -5.3734
Max Act: 4.9672. Min Act: -0.1700
Data Index: 5349158 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3734. Min Range: -5.3734
Max Act: 4.9672. Min Act: -0.1700
Data Index: 6330933 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3734. Min Range: -5.3734
Max Act: 4.9672. Min Act: -0.1700
Data Index: 280549 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3734. Min Range: -5.3734
Max Act: 4.9359. Min Act: -0.1700
Data Index: 6449796 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3734. Min Range: -5.3734
Max Act: 4.9672. Min Act: -0.1700
Data Index: 5084346 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3734. Min Range: -5.3734
Max Act: 4.9047. Min Act: -0.1700
Data Index: 4889709 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3734. Min Range: -5.3734
Max Act: 4.9047. Min Act: -0.1700
Data Index: 3528900 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #19