Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3490 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4807. Min Range: -5.4807
Max Act: 5.4807. Min Act: -0.1700
Data Index: 8485847 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4807. Min Range: -5.4807
Max Act: 5.4807. Min Act: -0.1700
Data Index: 2841548 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4807. Min Range: -5.4807
Max Act: 5.4495. Min Act: -0.1700
Data Index: 1054182 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4807. Min Range: -5.4807
Max Act: 5.3870. Min Act: -0.1700
Data Index: 2134041 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4807. Min Range: -5.4807
Max Act: 5.3245. Min Act: -0.1700
Data Index: 2289772 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4807. Min Range: -5.4807
Max Act: 5.3245. Min Act: -0.1700
Data Index: 4502958 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4807. Min Range: -5.4807
Max Act: 5.3245. Min Act: -0.1700
Data Index: 2217194 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4807. Min Range: -5.4807
Max Act: 5.2932. Min Act: -0.1700
Data Index: 6538527 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4807. Min Range: -5.4807
Max Act: 5.2307. Min Act: -0.1700
Data Index: 4281781 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4807. Min Range: -5.4807
Max Act: 5.1995. Min Act: -0.1700
Data Index: 6875723 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4807. Min Range: -5.4807
Max Act: 5.2307. Min Act: -0.1700
Data Index: 4281780 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4807. Min Range: -5.4807
Max Act: 5.1995. Min Act: -0.1700
Data Index: 8764108 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4807. Min Range: -5.4807
Max Act: 5.2307. Min Act: -0.1700
Data Index: 113116 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4807. Min Range: -5.4807
Max Act: 5.1995. Min Act: -0.1700
Data Index: 8592908 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4807. Min Range: -5.4807
Max Act: 5.1682. Min Act: -0.1700
Data Index: 3069441 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4807. Min Range: -5.4807
Max Act: 5.1682. Min Act: -0.1700
Data Index: 6601004 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4807. Min Range: -5.4807
Max Act: 5.1682. Min Act: -0.1700
Data Index: 4142269 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4807. Min Range: -5.4807
Max Act: 5.1682. Min Act: -0.1700
Data Index: 5403790 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4807. Min Range: -5.4807
Max Act: 5.1370. Min Act: -0.1700
Data Index: 3069442 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4807. Min Range: -5.4807
Max Act: 5.1370. Min Act: -0.1700
Data Index: 2052227 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19