Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 571 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4299. Min Range: -4.4299
Max Act: 4.4299. Min Act: -0.1700
Data Index: 1622568 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4299. Min Range: -4.4299
Max Act: 4.3674. Min Act: -0.1700
Data Index: 1957448 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4299. Min Range: -4.4299
Max Act: 4.3361. Min Act: -0.1700
Data Index: 2066366 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4299. Min Range: -4.4299
Max Act: 4.2736. Min Act: -0.1700
Data Index: 8442841 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4299. Min Range: -4.4299
Max Act: 4.2736. Min Act: -0.1700
Data Index: 3385155 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4299. Min Range: -4.4299
Max Act: 4.3049. Min Act: -0.1700
Data Index: 4540734 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4299. Min Range: -4.4299
Max Act: 4.2736. Min Act: -0.1700
Data Index: 7678074 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4299. Min Range: -4.4299
Max Act: 4.2424. Min Act: -0.1700
Data Index: 1114115 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4299. Min Range: -4.4299
Max Act: 4.2424. Min Act: -0.1700
Data Index: 4161773 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4299. Min Range: -4.4299
Max Act: 4.2424. Min Act: -0.1700
Data Index: 3097156 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4299. Min Range: -4.4299
Max Act: 4.2736. Min Act: -0.1700
Data Index: 2767513 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4299. Min Range: -4.4299
Max Act: 4.2424. Min Act: -0.1700
Data Index: 8376188 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4299. Min Range: -4.4299
Max Act: 4.2424. Min Act: -0.1700
Data Index: 1066163 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4299. Min Range: -4.4299
Max Act: 4.2424. Min Act: -0.1700
Data Index: 1767552 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4299. Min Range: -4.4299
Max Act: 4.2424. Min Act: -0.1700
Data Index: 8821453 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4299. Min Range: -4.4299
Max Act: 4.2111. Min Act: -0.1700
Data Index: 5092146 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4299. Min Range: -4.4299
Max Act: 4.2111. Min Act: -0.1700
Data Index: 8010967 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4299. Min Range: -4.4299
Max Act: 4.1798. Min Act: -0.1700
Data Index: 6133090 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4299. Min Range: -4.4299
Max Act: 4.1798. Min Act: -0.1700
Data Index: 7135786 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4299. Min Range: -4.4299
Max Act: 4.1486. Min Act: -0.1700
Data Index: 4277069 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19