Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5651 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1917. Min Range: -3.1917
Max Act: 3.1917. Min Act: -0.1700
Data Index: 6813933 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1917. Min Range: -3.1917
Max Act: 3.1917. Min Act: -0.1700
Data Index: 5499781 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1917. Min Range: -3.1917
Max Act: 3.1759. Min Act: -0.1700
Data Index: 6905752 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1917. Min Range: -3.1917
Max Act: 3.1759. Min Act: -0.1700
Data Index: 1801197 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1917. Min Range: -3.1917
Max Act: 3.1602. Min Act: -0.1700
Data Index: 2051383 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1917. Min Range: -3.1917
Max Act: 3.1445. Min Act: -0.1700
Data Index: 259905 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1917. Min Range: -3.1917
Max Act: 3.1445. Min Act: -0.1700
Data Index: 7852144 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1917. Min Range: -3.1917
Max Act: 3.1130. Min Act: -0.1700
Data Index: 2122259 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1917. Min Range: -3.1917
Max Act: 3.1445. Min Act: -0.1700
Data Index: 6236488 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1917. Min Range: -3.1917
Max Act: 3.1130. Min Act: -0.1700
Data Index: 4551607 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1917. Min Range: -3.1917
Max Act: 3.1130. Min Act: -0.1700
Data Index: 1180204 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1917. Min Range: -3.1917
Max Act: 3.0814. Min Act: -0.1700
Data Index: 1135888 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1917. Min Range: -3.1917
Max Act: 3.0499. Min Act: -0.1700
Data Index: 3843667 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1917. Min Range: -3.1917
Max Act: 3.0499. Min Act: -0.1700
Data Index: 3266009 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1917. Min Range: -3.1917
Max Act: 3.0499. Min Act: -0.1700
Data Index: 727138 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1917. Min Range: -3.1917
Max Act: 3.0499. Min Act: -0.1700
Data Index: 4351953 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1917. Min Range: -3.1917
Max Act: 3.0183. Min Act: -0.1700
Data Index: 6618391 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1917. Min Range: -3.1917
Max Act: 3.0341. Min Act: -0.1700
Data Index: 1469520 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1917. Min Range: -3.1917
Max Act: 3.0025. Min Act: -0.1700
Data Index: 2985353 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1917. Min Range: -3.1917
Max Act: 3.0025. Min Act: -0.1700
Data Index: 2902778 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19