Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2386 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0276. Min Range: -3.0276
Max Act: 3.0276. Min Act: -0.1700
Data Index: 2830450 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0276. Min Range: -3.0276
Max Act: 2.9327. Min Act: -0.1700
Data Index: 4041624 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0276. Min Range: -3.0276
Max Act: 2.8852. Min Act: -0.1700
Data Index: 756354 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0276. Min Range: -3.0276
Max Act: 2.9010. Min Act: -0.1700
Data Index: 968040 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0276. Min Range: -3.0276
Max Act: 2.8693. Min Act: -0.1700
Data Index: 6146611 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0276. Min Range: -3.0276
Max Act: 2.8852. Min Act: -0.1700
Data Index: 7568361 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0276. Min Range: -3.0276
Max Act: 2.8693. Min Act: -0.1700
Data Index: 4860042 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0276. Min Range: -3.0276
Max Act: 2.8534. Min Act: -0.1700
Data Index: 7844913 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0276. Min Range: -3.0276
Max Act: 2.8375. Min Act: -0.1700
Data Index: 6422366 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0276. Min Range: -3.0276
Max Act: 2.8534. Min Act: -0.1700
Data Index: 1277300 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0276. Min Range: -3.0276
Max Act: 2.8057. Min Act: -0.1700
Data Index: 4417008 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0276. Min Range: -3.0276
Max Act: 2.8216. Min Act: -0.1700
Data Index: 8121510 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0276. Min Range: -3.0276
Max Act: 2.8057. Min Act: -0.1700
Data Index: 8438049 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0276. Min Range: -3.0276
Max Act: 2.7898. Min Act: -0.1700
Data Index: 40465 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0276. Min Range: -3.0276
Max Act: 2.7739. Min Act: -0.1700
Data Index: 8546886 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0276. Min Range: -3.0276
Max Act: 2.7739. Min Act: -0.1700
Data Index: 8079698 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0276. Min Range: -3.0276
Max Act: 2.7419. Min Act: -0.1700
Data Index: 2275884 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0276. Min Range: -3.0276
Max Act: 2.7419. Min Act: -0.1700
Data Index: 890560 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0276. Min Range: -3.0276
Max Act: 2.7419. Min Act: -0.1700
Data Index: 6407057 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0276. Min Range: -3.0276
Max Act: 2.7260. Min Act: -0.1700
Data Index: 5825522 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19