Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 475 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7884. Min Range: -2.7884
Max Act: 2.7884. Min Act: -0.1700
Data Index: 696017 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7884. Min Range: -2.7884
Max Act: 2.7565. Min Act: -0.1700
Data Index: 1740344 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7884. Min Range: -2.7884
Max Act: 2.7086. Min Act: -0.1700
Data Index: 834751 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7884. Min Range: -2.7884
Max Act: 2.6606. Min Act: -0.1700
Data Index: 2970564 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7884. Min Range: -2.7884
Max Act: 2.6445. Min Act: -0.1700
Data Index: 6965386 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7884. Min Range: -2.7884
Max Act: 2.6445. Min Act: -0.1700
Data Index: 5231970 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7884. Min Range: -2.7884
Max Act: 2.6285. Min Act: -0.1700
Data Index: 6925022 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7884. Min Range: -2.7884
Max Act: 2.6285. Min Act: -0.1700
Data Index: 6795317 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7884. Min Range: -2.7884
Max Act: 2.6285. Min Act: -0.1700
Data Index: 1898775 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7884. Min Range: -2.7884
Max Act: 2.5963. Min Act: -0.1700
Data Index: 2253553 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7884. Min Range: -2.7884
Max Act: 2.5802. Min Act: -0.1700
Data Index: 6007629 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7884. Min Range: -2.7884
Max Act: 2.5802. Min Act: -0.1700
Data Index: 3378880 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7884. Min Range: -2.7884
Max Act: 2.5641. Min Act: -0.1700
Data Index: 4310510 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7884. Min Range: -2.7884
Max Act: 2.5641. Min Act: -0.1700
Data Index: 3341450 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7884. Min Range: -2.7884
Max Act: 2.5479. Min Act: -0.1700
Data Index: 3168265 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7884. Min Range: -2.7884
Max Act: 2.5479. Min Act: -0.1700
Data Index: 1205493 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7884. Min Range: -2.7884
Max Act: 2.5479. Min Act: -0.1700
Data Index: 1867255 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7884. Min Range: -2.7884
Max Act: 2.5479. Min Act: -0.1700
Data Index: 6725907 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7884. Min Range: -2.7884
Max Act: 2.5479. Min Act: -0.1700
Data Index: 1462100 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7884. Min Range: -2.7884
Max Act: 2.5479. Min Act: -0.1700
Data Index: 5621150 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19