Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3696 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0691. Min Range: -8.0691
Max Act: 8.0691. Min Act: -0.1700
Data Index: 1285904 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0691. Min Range: -8.0691
Max Act: 8.0066. Min Act: -0.1700
Data Index: 4483261 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0691. Min Range: -8.0691
Max Act: 8.0066. Min Act: -0.1700
Data Index: 4104868 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0691. Min Range: -8.0691
Max Act: 7.9441. Min Act: -0.1700
Data Index: 2069574 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0691. Min Range: -8.0691
Max Act: 7.9441. Min Act: -0.1700
Data Index: 1876127 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0691. Min Range: -8.0691
Max Act: 7.9441. Min Act: -0.1700
Data Index: 4104851 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0691. Min Range: -8.0691
Max Act: 7.9441. Min Act: -0.1700
Data Index: 1842060 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0691. Min Range: -8.0691
Max Act: 7.9441. Min Act: -0.1700
Data Index: 5163682 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0691. Min Range: -8.0691
Max Act: 7.8816. Min Act: -0.1700
Data Index: 3219459 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0691. Min Range: -8.0691
Max Act: 7.8191. Min Act: -0.1700
Data Index: 1645485 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0691. Min Range: -8.0691
Max Act: 7.8816. Min Act: -0.1700
Data Index: 1303 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0691. Min Range: -8.0691
Max Act: 7.8816. Min Act: -0.1700
Data Index: 4104874 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0691. Min Range: -8.0691
Max Act: 7.8816. Min Act: -0.1700
Data Index: 8193901 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0691. Min Range: -8.0691
Max Act: 7.8816. Min Act: -0.1700
Data Index: 8164494 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0691. Min Range: -8.0691
Max Act: 7.8816. Min Act: -0.1700
Data Index: 5163684 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0691. Min Range: -8.0691
Max Act: 7.8816. Min Act: -0.1700
Data Index: 1222853 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0691. Min Range: -8.0691
Max Act: 7.8191. Min Act: -0.1700
Data Index: 2069573 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0691. Min Range: -8.0691
Max Act: 7.8191. Min Act: -0.1700
Data Index: 1179421 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0691. Min Range: -8.0691
Max Act: 7.8191. Min Act: -0.1700
Data Index: 1842062 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0691. Min Range: -8.0691
Max Act: 7.8191. Min Act: -0.1700
Data Index: 1842061 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19