Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1787 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4217. Min Range: -9.4217
Max Act: 9.4217. Min Act: -0.1700
Data Index: 2151927 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4217. Min Range: -9.4217
Max Act: 9.2967. Min Act: -0.1700
Data Index: 8573582 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4217. Min Range: -9.4217
Max Act: 9.1092. Min Act: -0.1700
Data Index: 4534520 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4217. Min Range: -9.4217
Max Act: 8.9842. Min Act: -0.1700
Data Index: 6465436 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4217. Min Range: -9.4217
Max Act: 8.8592. Min Act: -0.1700
Data Index: 2721400 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4217. Min Range: -9.4217
Max Act: 8.9217. Min Act: -0.1700
Data Index: 4899932 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4217. Min Range: -9.4217
Max Act: 8.8592. Min Act: -0.1700
Data Index: 2039472 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4217. Min Range: -9.4217
Max Act: 8.8592. Min Act: -0.1700
Data Index: 7709907 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4217. Min Range: -9.4217
Max Act: 8.7967. Min Act: -0.1700
Data Index: 8442655 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4217. Min Range: -9.4217
Max Act: 8.7967. Min Act: -0.1700
Data Index: 2721397 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4217. Min Range: -9.4217
Max Act: 8.7342. Min Act: -0.1700
Data Index: 7617888 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4217. Min Range: -9.4217
Max Act: 8.7342. Min Act: -0.1700
Data Index: 2286750 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4217. Min Range: -9.4217
Max Act: 8.7342. Min Act: -0.1700
Data Index: 867306 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4217. Min Range: -9.4217
Max Act: 8.6717. Min Act: -0.1700
Data Index: 2046358 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4217. Min Range: -9.4217
Max Act: 8.6717. Min Act: -0.1700
Data Index: 5235239 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4217. Min Range: -9.4217
Max Act: 8.6717. Min Act: -0.1700
Data Index: 5941952 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4217. Min Range: -9.4217
Max Act: 8.6092. Min Act: -0.1700
Data Index: 8223689 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4217. Min Range: -9.4217
Max Act: 8.6092. Min Act: -0.1700
Data Index: 6201962 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4217. Min Range: -9.4217
Max Act: 8.5467. Min Act: -0.1700
Data Index: 2091086 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4217. Min Range: -9.4217
Max Act: 8.5467. Min Act: -0.1700
Data Index: 5699700 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19