Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3761 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.6602. Min Range: -11.6602
Max Act: 11.6602. Min Act: -0.1700
Data Index: 6777866 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.6602. Min Range: -11.6602
Max Act: 11.6602. Min Act: -0.1700
Data Index: 6819997 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.6602. Min Range: -11.6602
Max Act: 11.6602. Min Act: -0.1700
Data Index: 6056955 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.6602. Min Range: -11.6602
Max Act: 11.5977. Min Act: -0.1700
Data Index: 7100744 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.6602. Min Range: -11.6602
Max Act: 11.5352. Min Act: -0.1700
Data Index: 4129186 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.6602. Min Range: -11.6602
Max Act: 11.4727. Min Act: -0.1700
Data Index: 2517332 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.6602. Min Range: -11.6602
Max Act: 11.4727. Min Act: -0.1700
Data Index: 5494965 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.6602. Min Range: -11.6602
Max Act: 11.4102. Min Act: -0.1700
Data Index: 2133210 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.6602. Min Range: -11.6602
Max Act: 11.2852. Min Act: -0.1700
Data Index: 1296959 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.6602. Min Range: -11.6602
Max Act: 11.2852. Min Act: -0.1700
Data Index: 486621 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.6602. Min Range: -11.6602
Max Act: 11.2227. Min Act: -0.1700
Data Index: 8693759 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.6602. Min Range: -11.6602
Max Act: 11.2227. Min Act: -0.1700
Data Index: 7203853 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.6602. Min Range: -11.6602
Max Act: 11.1602. Min Act: -0.1700
Data Index: 6911197 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.6602. Min Range: -11.6602
Max Act: 11.1602. Min Act: -0.1700
Data Index: 2282832 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.6602. Min Range: -11.6602
Max Act: 11.0977. Min Act: -0.1700
Data Index: 1676677 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.6602. Min Range: -11.6602
Max Act: 11.0977. Min Act: -0.1700
Data Index: 4059726 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.6602. Min Range: -11.6602
Max Act: 11.0977. Min Act: -0.1700
Data Index: 1924135 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.6602. Min Range: -11.6602
Max Act: 11.1602. Min Act: -0.1700
Data Index: 4709723 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.6602. Min Range: -11.6602
Max Act: 11.0977. Min Act: -0.1700
Data Index: 3765325 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.6602. Min Range: -11.6602
Max Act: 11.0352. Min Act: -0.1700
Data Index: 4910638 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #19