Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 176 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6853. Min Range: -5.6853
Max Act: 5.6853. Min Act: -0.1700
Data Index: 3547825 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6853. Min Range: -5.6853
Max Act: 5.6228. Min Act: -0.1700
Data Index: 4946673 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6853. Min Range: -5.6853
Max Act: 5.4978. Min Act: -0.1700
Data Index: 5388584 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6853. Min Range: -5.6853
Max Act: 5.3728. Min Act: -0.1700
Data Index: 4398896 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6853. Min Range: -5.6853
Max Act: 5.3728. Min Act: -0.1700
Data Index: 7481533 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6853. Min Range: -5.6853
Max Act: 5.3728. Min Act: -0.1700
Data Index: 7503560 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6853. Min Range: -5.6853
Max Act: 5.3728. Min Act: -0.1700
Data Index: 3338788 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6853. Min Range: -5.6853
Max Act: 5.3415. Min Act: -0.1700
Data Index: 4015834 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6853. Min Range: -5.6853
Max Act: 5.3415. Min Act: -0.1700
Data Index: 8670229 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6853. Min Range: -5.6853
Max Act: 5.3415. Min Act: -0.1700
Data Index: 1597511 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6853. Min Range: -5.6853
Max Act: 5.2790. Min Act: -0.1700
Data Index: 4864048 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6853. Min Range: -5.6853
Max Act: 5.2790. Min Act: -0.1700
Data Index: 4349427 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6853. Min Range: -5.6853
Max Act: 5.3103. Min Act: -0.1700
Data Index: 1041154 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6853. Min Range: -5.6853
Max Act: 5.3103. Min Act: -0.1700
Data Index: 1407303 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6853. Min Range: -5.6853
Max Act: 5.2478. Min Act: -0.1700
Data Index: 8029582 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6853. Min Range: -5.6853
Max Act: 5.2478. Min Act: -0.1700
Data Index: 4056560 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6853. Min Range: -5.6853
Max Act: 5.2478. Min Act: -0.1700
Data Index: 1419868 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6853. Min Range: -5.6853
Max Act: 5.2478. Min Act: -0.1700
Data Index: 2584252 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6853. Min Range: -5.6853
Max Act: 5.2478. Min Act: -0.1700
Data Index: 4673053 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6853. Min Range: -5.6853
Max Act: 5.2478. Min Act: -0.1700
Data Index: 668989 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19