Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1980 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3924. Min Range: -5.3924
Max Act: 5.3924. Min Act: -0.1700
Data Index: 5899512 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3924. Min Range: -5.3924
Max Act: 4.9549. Min Act: -0.1700
Data Index: 7018751 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3924. Min Range: -5.3924
Max Act: 4.9549. Min Act: -0.1700
Data Index: 6606751 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3924. Min Range: -5.3924
Max Act: 4.9237. Min Act: -0.1700
Data Index: 3141210 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3924. Min Range: -5.3924
Max Act: 4.9237. Min Act: -0.1700
Data Index: 2410546 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3924. Min Range: -5.3924
Max Act: 4.9237. Min Act: -0.1700
Data Index: 5050469 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3924. Min Range: -5.3924
Max Act: 4.8924. Min Act: -0.1700
Data Index: 1751890 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3924. Min Range: -5.3924
Max Act: 4.8612. Min Act: -0.1700
Data Index: 3777756 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3924. Min Range: -5.3924
Max Act: 4.8299. Min Act: -0.1700
Data Index: 1323740 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3924. Min Range: -5.3924
Max Act: 4.8299. Min Act: -0.1700
Data Index: 6345875 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3924. Min Range: -5.3924
Max Act: 4.7674. Min Act: -0.1700
Data Index: 1930214 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3924. Min Range: -5.3924
Max Act: 4.7674. Min Act: -0.1700
Data Index: 2324864 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3924. Min Range: -5.3924
Max Act: 4.7674. Min Act: -0.1700
Data Index: 4934448 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3924. Min Range: -5.3924
Max Act: 4.7674. Min Act: -0.1700
Data Index: 3822863 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3924. Min Range: -5.3924
Max Act: 4.7049. Min Act: -0.1700
Data Index: 3461844 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3924. Min Range: -5.3924
Max Act: 4.7049. Min Act: -0.1700
Data Index: 5778378 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3924. Min Range: -5.3924
Max Act: 4.7049. Min Act: -0.1700
Data Index: 428 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3924. Min Range: -5.3924
Max Act: 4.7049. Min Act: -0.1700
Data Index: 7259835 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3924. Min Range: -5.3924
Max Act: 4.6737. Min Act: -0.1700
Data Index: 383662 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3924. Min Range: -5.3924
Max Act: 4.6737. Min Act: -0.1700
Data Index: 5965839 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #19