Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3752 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9720. Min Range: -5.9720
Max Act: 5.9720. Min Act: -0.1700
Data Index: 4308426 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9720. Min Range: -5.9720
Max Act: 5.9095. Min Act: -0.1700
Data Index: 3665412 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9720. Min Range: -5.9720
Max Act: 5.8158. Min Act: -0.1700
Data Index: 8505554 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9720. Min Range: -5.9720
Max Act: 5.6908. Min Act: -0.1700
Data Index: 6406670 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9720. Min Range: -5.9720
Max Act: 5.6283. Min Act: -0.1700
Data Index: 194635 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9720. Min Range: -5.9720
Max Act: 5.6595. Min Act: -0.1700
Data Index: 4271307 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9720. Min Range: -5.9720
Max Act: 5.6283. Min Act: -0.1700
Data Index: 1309712 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9720. Min Range: -5.9720
Max Act: 5.5970. Min Act: -0.1700
Data Index: 3886281 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9720. Min Range: -5.9720
Max Act: 5.5970. Min Act: -0.1700
Data Index: 7591723 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9720. Min Range: -5.9720
Max Act: 5.5970. Min Act: -0.1700
Data Index: 8070908 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9720. Min Range: -5.9720
Max Act: 5.5658. Min Act: -0.1700
Data Index: 5615079 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9720. Min Range: -5.9720
Max Act: 5.5345. Min Act: -0.1700
Data Index: 2356538 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9720. Min Range: -5.9720
Max Act: 5.5345. Min Act: -0.1700
Data Index: 2677518 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9720. Min Range: -5.9720
Max Act: 5.5658. Min Act: -0.1700
Data Index: 3665420 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9720. Min Range: -5.9720
Max Act: 5.5345. Min Act: -0.1700
Data Index: 5615092 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9720. Min Range: -5.9720
Max Act: 5.5345. Min Act: -0.1700
Data Index: 4439066 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9720. Min Range: -5.9720
Max Act: 5.5345. Min Act: -0.1700
Data Index: 1598319 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9720. Min Range: -5.9720
Max Act: 5.5345. Min Act: -0.1700
Data Index: 5615090 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9720. Min Range: -5.9720
Max Act: 5.5345. Min Act: -0.1700
Data Index: 1056081 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9720. Min Range: -5.9720
Max Act: 5.5345. Min Act: -0.1700
Data Index: 3533606 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19