Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2744 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3477. Min Range: -9.3477
Max Act: 9.2852. Min Act: -0.1700
Data Index: 1055355 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3477. Min Range: -9.3477
Max Act: 9.3477. Min Act: -0.1700
Data Index: 8779044 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3477. Min Range: -9.3477
Max Act: 9.2852. Min Act: -0.1700
Data Index: 749378 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3477. Min Range: -9.3477
Max Act: 9.2852. Min Act: -0.1700
Data Index: 8282248 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3477. Min Range: -9.3477
Max Act: 9.0977. Min Act: -0.1700
Data Index: 3966374 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3477. Min Range: -9.3477
Max Act: 9.0977. Min Act: -0.1700
Data Index: 6456874 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3477. Min Range: -9.3477
Max Act: 9.1602. Min Act: -0.1700
Data Index: 5667673 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3477. Min Range: -9.3477
Max Act: 9.1602. Min Act: -0.1700
Data Index: 3154108 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3477. Min Range: -9.3477
Max Act: 9.1602. Min Act: -0.1700
Data Index: 3913812 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3477. Min Range: -9.3477
Max Act: 9.0977. Min Act: -0.1700
Data Index: 1051988 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3477. Min Range: -9.3477
Max Act: 9.0977. Min Act: -0.1700
Data Index: 946252 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3477. Min Range: -9.3477
Max Act: 9.0977. Min Act: -0.1700
Data Index: 5088022 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3477. Min Range: -9.3477
Max Act: 9.0352. Min Act: -0.1700
Data Index: 4239392 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3477. Min Range: -9.3477
Max Act: 9.0352. Min Act: -0.1700
Data Index: 251415 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3477. Min Range: -9.3477
Max Act: 9.0352. Min Act: -0.1700
Data Index: 8327466 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3477. Min Range: -9.3477
Max Act: 9.0977. Min Act: -0.1700
Data Index: 1125124 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3477. Min Range: -9.3477
Max Act: 9.0352. Min Act: -0.1700
Data Index: 7692470 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3477. Min Range: -9.3477
Max Act: 9.0977. Min Act: -0.1700
Data Index: 7691155 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3477. Min Range: -9.3477
Max Act: 8.9727. Min Act: -0.1700
Data Index: 7242154 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3477. Min Range: -9.3477
Max Act: 8.9727. Min Act: -0.1700
Data Index: 7679178 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #19