Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1828 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6200. Min Range: -6.6200
Max Act: 6.6200. Min Act: -0.1700
Data Index: 7296915 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6200. Min Range: -6.6200
Max Act: 6.6200. Min Act: -0.1700
Data Index: 592136 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6200. Min Range: -6.6200
Max Act: 6.5263. Min Act: -0.1700
Data Index: 2262280 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6200. Min Range: -6.6200
Max Act: 6.4638. Min Act: -0.1700
Data Index: 8341752 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6200. Min Range: -6.6200
Max Act: 6.3700. Min Act: -0.1700
Data Index: 7804829 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6200. Min Range: -6.6200
Max Act: 6.3075. Min Act: -0.1700
Data Index: 2273081 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6200. Min Range: -6.6200
Max Act: 6.3075. Min Act: -0.1700
Data Index: 5197192 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6200. Min Range: -6.6200
Max Act: 6.3388. Min Act: -0.1700
Data Index: 3668883 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6200. Min Range: -6.6200
Max Act: 6.3388. Min Act: -0.1700
Data Index: 4121550 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6200. Min Range: -6.6200
Max Act: 6.1825. Min Act: -0.1700
Data Index: 4123615 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6200. Min Range: -6.6200
Max Act: 6.1825. Min Act: -0.1700
Data Index: 636687 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6200. Min Range: -6.6200
Max Act: 6.1200. Min Act: -0.1700
Data Index: 1086793 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6200. Min Range: -6.6200
Max Act: 6.0888. Min Act: -0.1700
Data Index: 3814951 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6200. Min Range: -6.6200
Max Act: 6.0263. Min Act: -0.1700
Data Index: 7242646 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6200. Min Range: -6.6200
Max Act: 6.0575. Min Act: -0.1700
Data Index: 2172158 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6200. Min Range: -6.6200
Max Act: 6.0575. Min Act: -0.1700
Data Index: 8158291 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6200. Min Range: -6.6200
Max Act: 5.9950. Min Act: -0.1700
Data Index: 5481136 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6200. Min Range: -6.6200
Max Act: 5.9638. Min Act: -0.1700
Data Index: 6092303 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6200. Min Range: -6.6200
Max Act: 5.9950. Min Act: -0.1700
Data Index: 2494042 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6200. Min Range: -6.6200
Max Act: 5.9950. Min Act: -0.1700
Data Index: 1836508 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19