Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1644 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3186. Min Range: -3.3186
Max Act: 3.3186. Min Act: -0.1700
Data Index: 7207524 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3186. Min Range: -3.3186
Max Act: 3.3029. Min Act: -0.1700
Data Index: 2010388 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3186. Min Range: -3.3186
Max Act: 3.2400. Min Act: -0.1700
Data Index: 8755398 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3186. Min Range: -3.3186
Max Act: 3.2086. Min Act: -0.1700
Data Index: 5698896 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3186. Min Range: -3.3186
Max Act: 3.1771. Min Act: -0.1700
Data Index: 6634724 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3186. Min Range: -3.3186
Max Act: 3.1457. Min Act: -0.1700
Data Index: 7315007 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3186. Min Range: -3.3186
Max Act: 3.1299. Min Act: -0.1700
Data Index: 8755397 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3186. Min Range: -3.3186
Max Act: 3.1299. Min Act: -0.1700
Data Index: 3718959 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3186. Min Range: -3.3186
Max Act: 3.1142. Min Act: -0.1700
Data Index: 6817846 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3186. Min Range: -3.3186
Max Act: 3.1142. Min Act: -0.1700
Data Index: 5109770 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3186. Min Range: -3.3186
Max Act: 3.1142. Min Act: -0.1700
Data Index: 2974080 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3186. Min Range: -3.3186
Max Act: 3.0826. Min Act: -0.1700
Data Index: 5391490 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3186. Min Range: -3.3186
Max Act: 3.0826. Min Act: -0.1700
Data Index: 3718957 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3186. Min Range: -3.3186
Max Act: 3.0984. Min Act: -0.1700
Data Index: 4178651 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3186. Min Range: -3.3186
Max Act: 3.0826. Min Act: -0.1700
Data Index: 8191811 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3186. Min Range: -3.3186
Max Act: 3.0669. Min Act: -0.1700
Data Index: 4532887 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3186. Min Range: -3.3186
Max Act: 3.0511. Min Act: -0.1700
Data Index: 4091997 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3186. Min Range: -3.3186
Max Act: 3.0511. Min Act: -0.1700
Data Index: 6994935 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3186. Min Range: -3.3186
Max Act: 3.0511. Min Act: -0.1700
Data Index: 8003616 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3186. Min Range: -3.3186
Max Act: 3.0353. Min Act: -0.1700
Data Index: 1315954 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19