Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1800 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5599. Min Range: -8.5599
Max Act: 8.5599. Min Act: -0.1700
Data Index: 1053745 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5599. Min Range: -8.5599
Max Act: 8.3724. Min Act: -0.1700
Data Index: 1035084 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5599. Min Range: -8.5599
Max Act: 8.1849. Min Act: -0.1700
Data Index: 3638326 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5599. Min Range: -8.5599
Max Act: 8.1849. Min Act: -0.1700
Data Index: 3973185 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5599. Min Range: -8.5599
Max Act: 8.1224. Min Act: -0.1700
Data Index: 957286 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5599. Min Range: -8.5599
Max Act: 8.1224. Min Act: -0.1700
Data Index: 196469 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5599. Min Range: -8.5599
Max Act: 7.9974. Min Act: -0.1700
Data Index: 7721180 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5599. Min Range: -8.5599
Max Act: 7.9037. Min Act: -0.1700
Data Index: 8641855 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5599. Min Range: -8.5599
Max Act: 7.8724. Min Act: -0.1700
Data Index: 3690966 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5599. Min Range: -8.5599
Max Act: 7.8412. Min Act: -0.1700
Data Index: 5003915 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5599. Min Range: -8.5599
Max Act: 7.8412. Min Act: -0.1700
Data Index: 7373422 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5599. Min Range: -8.5599
Max Act: 7.7787. Min Act: -0.1700
Data Index: 1176567 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5599. Min Range: -8.5599
Max Act: 7.7787. Min Act: -0.1700
Data Index: 2825741 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5599. Min Range: -8.5599
Max Act: 7.7787. Min Act: -0.1700
Data Index: 2347839 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5599. Min Range: -8.5599
Max Act: 7.7162. Min Act: -0.1700
Data Index: 5477753 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5599. Min Range: -8.5599
Max Act: 7.7474. Min Act: -0.1700
Data Index: 7193593 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5599. Min Range: -8.5599
Max Act: 7.7162. Min Act: -0.1700
Data Index: 5468983 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5599. Min Range: -8.5599
Max Act: 7.6537. Min Act: -0.1700
Data Index: 1771690 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5599. Min Range: -8.5599
Max Act: 7.6537. Min Act: -0.1700
Data Index: 2048609 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5599. Min Range: -8.5599
Max Act: 7.6537. Min Act: -0.1700
Data Index: 1468796 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19