Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5389 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 26.7820. Min Range: -26.7820
Max Act: 26.7820. Min Act: -0.1700
Data Index: 4809960 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 26.7820. Min Range: -26.7820
Max Act: 26.4070. Min Act: -0.1700
Data Index: 276907 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 26.7820. Min Range: -26.7820
Max Act: 26.2820. Min Act: -0.1700
Data Index: 5181097 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 26.7820. Min Range: -26.7820
Max Act: 26.0320. Min Act: -0.1700
Data Index: 5100178 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 26.7820. Min Range: -26.7820
Max Act: 26.1570. Min Act: -0.1700
Data Index: 6932829 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 26.7820. Min Range: -26.7820
Max Act: 26.1570. Min Act: -0.1700
Data Index: 6865827 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 26.7820. Min Range: -26.7820
Max Act: 26.1570. Min Act: -0.1700
Data Index: 8752132 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 26.7820. Min Range: -26.7820
Max Act: 26.0320. Min Act: -0.1700
Data Index: 3958747 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 26.7820. Min Range: -26.7820
Max Act: 26.0320. Min Act: -0.1700
Data Index: 1396187 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 26.7820. Min Range: -26.7820
Max Act: 26.0320. Min Act: -0.1700
Data Index: 4088061 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 26.7820. Min Range: -26.7820
Max Act: 25.9070. Min Act: -0.1700
Data Index: 8588883 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 26.7820. Min Range: -26.7820
Max Act: 25.9070. Min Act: -0.1700
Data Index: 5100177 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 26.7820. Min Range: -26.7820
Max Act: 25.9070. Min Act: -0.1700
Data Index: 8062610 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 26.7820. Min Range: -26.7820
Max Act: 25.7820. Min Act: -0.1700
Data Index: 6272888 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 26.7820. Min Range: -26.7820
Max Act: 25.7820. Min Act: -0.1700
Data Index: 7872236 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 26.7820. Min Range: -26.7820
Max Act: 25.6570. Min Act: -0.1700
Data Index: 2137899 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 26.7820. Min Range: -26.7820
Max Act: 25.6570. Min Act: -0.1700
Data Index: 5068294 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 26.7820. Min Range: -26.7820
Max Act: 25.5320. Min Act: -0.1700
Data Index: 6756109 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 26.7820. Min Range: -26.7820
Max Act: 25.6570. Min Act: -0.1700
Data Index: 7122145 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 26.7820. Min Range: -26.7820
Max Act: 25.5320. Min Act: -0.1700
Data Index: 1632754 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #19