Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4244 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4080. Min Range: -6.4080
Max Act: 6.4080. Min Act: -0.1700
Data Index: 4760449 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4080. Min Range: -6.4080
Max Act: 6.3767. Min Act: -0.1700
Data Index: 2628464 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4080. Min Range: -6.4080
Max Act: 6.3767. Min Act: -0.1700
Data Index: 5565157 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4080. Min Range: -6.4080
Max Act: 6.2517. Min Act: -0.1700
Data Index: 2855470 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4080. Min Range: -6.4080
Max Act: 6.2205. Min Act: -0.1700
Data Index: 300995 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4080. Min Range: -6.4080
Max Act: 6.2205. Min Act: -0.1700
Data Index: 2876281 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4080. Min Range: -6.4080
Max Act: 6.1580. Min Act: -0.1700
Data Index: 462255 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4080. Min Range: -6.4080
Max Act: 6.1580. Min Act: -0.1700
Data Index: 2935382 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4080. Min Range: -6.4080
Max Act: 6.0642. Min Act: -0.1700
Data Index: 7074280 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4080. Min Range: -6.4080
Max Act: 6.0330. Min Act: -0.1700
Data Index: 255797 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4080. Min Range: -6.4080
Max Act: 6.0017. Min Act: -0.1700
Data Index: 2271264 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4080. Min Range: -6.4080
Max Act: 6.0017. Min Act: -0.1700
Data Index: 7608931 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4080. Min Range: -6.4080
Max Act: 6.0017. Min Act: -0.1700
Data Index: 5904358 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4080. Min Range: -6.4080
Max Act: 6.0017. Min Act: -0.1700
Data Index: 5444782 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4080. Min Range: -6.4080
Max Act: 5.9705. Min Act: -0.1700
Data Index: 7456665 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4080. Min Range: -6.4080
Max Act: 5.9392. Min Act: -0.1700
Data Index: 197894 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4080. Min Range: -6.4080
Max Act: 5.9080. Min Act: -0.1700
Data Index: 7386660 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4080. Min Range: -6.4080
Max Act: 5.9392. Min Act: -0.1700
Data Index: 3745273 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4080. Min Range: -6.4080
Max Act: 5.9392. Min Act: -0.1700
Data Index: 8331887 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4080. Min Range: -6.4080
Max Act: 5.9392. Min Act: -0.1700
Data Index: 8484982 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #19