Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5296 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0187. Min Range: -5.0187
Max Act: 5.0187. Min Act: -0.1700
Data Index: 904196 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.8312. Min Act: -0.1700
Data Index: 5966570 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.6750. Min Act: -0.1700
Data Index: 1099272 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.6437. Min Act: -0.1700
Data Index: 3908934 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.6437. Min Act: -0.1700
Data Index: 5105140 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.6750. Min Act: -0.1700
Data Index: 2348695 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.6125. Min Act: -0.1700
Data Index: 6910302 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.6125. Min Act: -0.1700
Data Index: 1848126 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.5812. Min Act: -0.1700
Data Index: 2954961 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.5812. Min Act: -0.1700
Data Index: 1697105 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.5187. Min Act: -0.1700
Data Index: 7941429 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.5500. Min Act: -0.1700
Data Index: 5355145 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.5500. Min Act: -0.1700
Data Index: 6994908 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.5500. Min Act: -0.1700
Data Index: 4154571 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.5187. Min Act: -0.1700
Data Index: 7319363 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.5187. Min Act: -0.1700
Data Index: 2590905 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.5187. Min Act: -0.1700
Data Index: 3185532 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.5187. Min Act: -0.1700
Data Index: 4625793 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.5187. Min Act: -0.1700
Data Index: 1223766 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.5187. Min Act: -0.1700
Data Index: 4713819 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #19