Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3506 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9298. Min Range: -2.9298
Max Act: 2.9298. Min Act: -0.1700
Data Index: 8352966 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9298. Min Range: -2.9298
Max Act: 2.9140. Min Act: -0.1700
Data Index: 32715 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9298. Min Range: -2.9298
Max Act: 2.8664. Min Act: -0.1700
Data Index: 5607454 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9298. Min Range: -2.9298
Max Act: 2.8822. Min Act: -0.1700
Data Index: 651390 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9298. Min Range: -2.9298
Max Act: 2.8505. Min Act: -0.1700
Data Index: 8529423 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9298. Min Range: -2.9298
Max Act: 2.7868. Min Act: -0.1700
Data Index: 5508921 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9298. Min Range: -2.9298
Max Act: 2.7868. Min Act: -0.1700
Data Index: 7355144 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9298. Min Range: -2.9298
Max Act: 2.7709. Min Act: -0.1700
Data Index: 3179250 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9298. Min Range: -2.9298
Max Act: 2.7709. Min Act: -0.1700
Data Index: 4227446 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9298. Min Range: -2.9298
Max Act: 2.7390. Min Act: -0.1700
Data Index: 1477422 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9298. Min Range: -2.9298
Max Act: 2.7230. Min Act: -0.1700
Data Index: 4996376 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9298. Min Range: -2.9298
Max Act: 2.7390. Min Act: -0.1700
Data Index: 4455139 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9298. Min Range: -2.9298
Max Act: 2.7230. Min Act: -0.1700
Data Index: 1427860 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9298. Min Range: -2.9298
Max Act: 2.7230. Min Act: -0.1700
Data Index: 1185589 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9298. Min Range: -2.9298
Max Act: 2.7230. Min Act: -0.1700
Data Index: 240342 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9298. Min Range: -2.9298
Max Act: 2.7390. Min Act: -0.1700
Data Index: 1464976 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9298. Min Range: -2.9298
Max Act: 2.7070. Min Act: -0.1700
Data Index: 453566 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9298. Min Range: -2.9298
Max Act: 2.7070. Min Act: -0.1700
Data Index: 1427884 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9298. Min Range: -2.9298
Max Act: 2.7070. Min Act: -0.1700
Data Index: 4192381 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9298. Min Range: -2.9298
Max Act: 2.7070. Min Act: -0.1700
Data Index: 8686249 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19