Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5565 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1437. Min Range: -7.1437
Max Act: 7.1437. Min Act: -0.1700
Data Index: 828065 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1437. Min Range: -7.1437
Max Act: 7.0187. Min Act: -0.1700
Data Index: 7621076 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1437. Min Range: -7.1437
Max Act: 6.9562. Min Act: -0.1700
Data Index: 230087 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1437. Min Range: -7.1437
Max Act: 6.9562. Min Act: -0.1700
Data Index: 111040 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1437. Min Range: -7.1437
Max Act: 6.8937. Min Act: -0.1700
Data Index: 1096472 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1437. Min Range: -7.1437
Max Act: 6.7687. Min Act: -0.1700
Data Index: 1394688 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1437. Min Range: -7.1437
Max Act: 6.6749. Min Act: -0.1700
Data Index: 8647902 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1437. Min Range: -7.1437
Max Act: 6.6749. Min Act: -0.1700
Data Index: 7777722 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1437. Min Range: -7.1437
Max Act: 6.6749. Min Act: -0.1700
Data Index: 2896920 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1437. Min Range: -7.1437
Max Act: 6.6437. Min Act: -0.1700
Data Index: 5550681 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1437. Min Range: -7.1437
Max Act: 6.6124. Min Act: -0.1700
Data Index: 4111175 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1437. Min Range: -7.1437
Max Act: 6.6437. Min Act: -0.1700
Data Index: 4172565 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1437. Min Range: -7.1437
Max Act: 6.6437. Min Act: -0.1700
Data Index: 4202497 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1437. Min Range: -7.1437
Max Act: 6.6124. Min Act: -0.1700
Data Index: 6532926 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1437. Min Range: -7.1437
Max Act: 6.5812. Min Act: -0.1700
Data Index: 858000 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1437. Min Range: -7.1437
Max Act: 6.5812. Min Act: -0.1700
Data Index: 7778799 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1437. Min Range: -7.1437
Max Act: 6.5187. Min Act: -0.1700
Data Index: 2494609 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1437. Min Range: -7.1437
Max Act: 6.5499. Min Act: -0.1700
Data Index: 1013669 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1437. Min Range: -7.1437
Max Act: 6.5187. Min Act: -0.1700
Data Index: 8007850 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1437. Min Range: -7.1437
Max Act: 6.5187. Min Act: -0.1700
Data Index: 7849365 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #19