Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1676 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.8709. Min Act: -0.1700
Data Index: 5654596 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.1522. Min Act: -0.1700
Data Index: 1004652 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.1522. Min Act: -0.1700
Data Index: 1716367 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.1522. Min Act: -0.1700
Data Index: 8710991 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.1522. Min Act: -0.1700
Data Index: 7053668 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.1209. Min Act: -0.1700
Data Index: 5929987 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.1209. Min Act: -0.1700
Data Index: 813615 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.0897. Min Act: -0.1700
Data Index: 2350730 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.0897. Min Act: -0.1700
Data Index: 909758 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.0897. Min Act: -0.1700
Data Index: 2933207 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.0272. Min Act: -0.1700
Data Index: 7710445 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.0584. Min Act: -0.1700
Data Index: 3026885 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.0584. Min Act: -0.1700
Data Index: 6769177 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.0584. Min Act: -0.1700
Data Index: 111869 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.0272. Min Act: -0.1700
Data Index: 5603742 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.0272. Min Act: -0.1700
Data Index: 679648 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8709. Min Range: -5.8709
Max Act: 4.9959. Min Act: -0.1700
Data Index: 1034695 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8709. Min Range: -5.8709
Max Act: 4.9959. Min Act: -0.1700
Data Index: 8168504 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.0272. Min Act: -0.1700
Data Index: 3068370 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8709. Min Range: -5.8709
Max Act: 4.9647. Min Act: -0.1700
Data Index: 4772223 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #19