Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3469 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0287. Min Range: -7.0287
Max Act: 7.0287. Min Act: -0.1700
Data Index: 36411 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0287. Min Range: -7.0287
Max Act: 6.5912. Min Act: -0.1700
Data Index: 4631816 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0287. Min Range: -7.0287
Max Act: 6.5287. Min Act: -0.1700
Data Index: 2880141 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0287. Min Range: -7.0287
Max Act: 6.5599. Min Act: -0.1700
Data Index: 6806868 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0287. Min Range: -7.0287
Max Act: 6.4974. Min Act: -0.1700
Data Index: 6296244 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0287. Min Range: -7.0287
Max Act: 6.4662. Min Act: -0.1700
Data Index: 1363405 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0287. Min Range: -7.0287
Max Act: 6.4349. Min Act: -0.1700
Data Index: 561082 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0287. Min Range: -7.0287
Max Act: 6.4662. Min Act: -0.1700
Data Index: 8450505 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0287. Min Range: -7.0287
Max Act: 6.4349. Min Act: -0.1700
Data Index: 3351597 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0287. Min Range: -7.0287
Max Act: 6.4349. Min Act: -0.1700
Data Index: 1229845 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0287. Min Range: -7.0287
Max Act: 6.4349. Min Act: -0.1700
Data Index: 2422131 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0287. Min Range: -7.0287
Max Act: 6.4662. Min Act: -0.1700
Data Index: 5586347 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0287. Min Range: -7.0287
Max Act: 6.4349. Min Act: -0.1700
Data Index: 4896322 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0287. Min Range: -7.0287
Max Act: 6.4349. Min Act: -0.1700
Data Index: 668788 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0287. Min Range: -7.0287
Max Act: 6.4037. Min Act: -0.1700
Data Index: 1678873 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0287. Min Range: -7.0287
Max Act: 6.4037. Min Act: -0.1700
Data Index: 5421701 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0287. Min Range: -7.0287
Max Act: 6.4037. Min Act: -0.1700
Data Index: 8799740 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0287. Min Range: -7.0287
Max Act: 6.3724. Min Act: -0.1700
Data Index: 1860135 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0287. Min Range: -7.0287
Max Act: 6.3724. Min Act: -0.1700
Data Index: 93566 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0287. Min Range: -7.0287
Max Act: 6.3724. Min Act: -0.1700
Data Index: 2621660 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19