Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4597 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9870. Min Range: -3.9870
Max Act: 3.9870. Min Act: -0.1700
Data Index: 6211967 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9870. Min Range: -3.9870
Max Act: 3.9245. Min Act: -0.1700
Data Index: 717696 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9870. Min Range: -3.9870
Max Act: 3.8932. Min Act: -0.1700
Data Index: 5088228 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9870. Min Range: -3.9870
Max Act: 3.8619. Min Act: -0.1700
Data Index: 7211242 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9870. Min Range: -3.9870
Max Act: 3.8619. Min Act: -0.1700
Data Index: 8204922 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9870. Min Range: -3.9870
Max Act: 3.8619. Min Act: -0.1700
Data Index: 1474442 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9870. Min Range: -3.9870
Max Act: 3.8619. Min Act: -0.1700
Data Index: 4432538 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9870. Min Range: -3.9870
Max Act: 3.8307. Min Act: -0.1700
Data Index: 4516892 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9870. Min Range: -3.9870
Max Act: 3.8307. Min Act: -0.1700
Data Index: 6792074 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9870. Min Range: -3.9870
Max Act: 3.8307. Min Act: -0.1700
Data Index: 558783 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9870. Min Range: -3.9870
Max Act: 3.7994. Min Act: -0.1700
Data Index: 2339497 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9870. Min Range: -3.9870
Max Act: 3.8619. Min Act: -0.1700
Data Index: 478360 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9870. Min Range: -3.9870
Max Act: 3.7994. Min Act: -0.1700
Data Index: 7794273 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9870. Min Range: -3.9870
Max Act: 3.7994. Min Act: -0.1700
Data Index: 5981013 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9870. Min Range: -3.9870
Max Act: 3.7681. Min Act: -0.1700
Data Index: 3666144 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9870. Min Range: -3.9870
Max Act: 3.7994. Min Act: -0.1700
Data Index: 5160469 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9870. Min Range: -3.9870
Max Act: 3.7681. Min Act: -0.1700
Data Index: 1213212 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9870. Min Range: -3.9870
Max Act: 3.7681. Min Act: -0.1700
Data Index: 6055169 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9870. Min Range: -3.9870
Max Act: 3.7681. Min Act: -0.1700
Data Index: 3893516 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9870. Min Range: -3.9870
Max Act: 3.7681. Min Act: -0.1700
Data Index: 5815008 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19