Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3391 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9787. Min Range: -8.9787
Max Act: 8.9787. Min Act: -0.1700
Data Index: 6595246 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9787. Min Range: -8.9787
Max Act: 8.7912. Min Act: -0.1700
Data Index: 3522172 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9787. Min Range: -8.9787
Max Act: 8.6662. Min Act: -0.1700
Data Index: 8179343 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9787. Min Range: -8.9787
Max Act: 8.5412. Min Act: -0.1700
Data Index: 8353304 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9787. Min Range: -8.9787
Max Act: 8.4787. Min Act: -0.1700
Data Index: 4905215 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9787. Min Range: -8.9787
Max Act: 8.4787. Min Act: -0.1700
Data Index: 691708 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9787. Min Range: -8.9787
Max Act: 8.4787. Min Act: -0.1700
Data Index: 5149998 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9787. Min Range: -8.9787
Max Act: 8.4787. Min Act: -0.1700
Data Index: 4736576 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9787. Min Range: -8.9787
Max Act: 8.5412. Min Act: -0.1700
Data Index: 1799927 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9787. Min Range: -8.9787
Max Act: 8.4787. Min Act: -0.1700
Data Index: 121365 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9787. Min Range: -8.9787
Max Act: 8.4162. Min Act: -0.1700
Data Index: 5570571 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9787. Min Range: -8.9787
Max Act: 8.4162. Min Act: -0.1700
Data Index: 8681717 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9787. Min Range: -8.9787
Max Act: 8.3537. Min Act: -0.1700
Data Index: 6057304 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9787. Min Range: -8.9787
Max Act: 8.3537. Min Act: -0.1700
Data Index: 4675966 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9787. Min Range: -8.9787
Max Act: 8.3537. Min Act: -0.1700
Data Index: 2294734 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9787. Min Range: -8.9787
Max Act: 8.3537. Min Act: -0.1700
Data Index: 7135780 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9787. Min Range: -8.9787
Max Act: 8.3537. Min Act: -0.1700
Data Index: 3862964 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9787. Min Range: -8.9787
Max Act: 8.2912. Min Act: -0.1700
Data Index: 2840745 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9787. Min Range: -8.9787
Max Act: 8.2912. Min Act: -0.1700
Data Index: 4234254 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9787. Min Range: -8.9787
Max Act: 8.3537. Min Act: -0.1700
Data Index: 3494970 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19