Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5135 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7937. Min Range: -3.7937
Max Act: 3.7937. Min Act: -0.1700
Data Index: 8044012 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7937. Min Range: -3.7937
Max Act: 3.7311. Min Act: -0.1700
Data Index: 7687977 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7937. Min Range: -3.7937
Max Act: 3.6999. Min Act: -0.1700
Data Index: 1124037 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7937. Min Range: -3.7937
Max Act: 3.6999. Min Act: -0.1700
Data Index: 7956955 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7937. Min Range: -3.7937
Max Act: 3.6999. Min Act: -0.1700
Data Index: 4988974 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7937. Min Range: -3.7937
Max Act: 3.6999. Min Act: -0.1700
Data Index: 4205665 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7937. Min Range: -3.7937
Max Act: 3.6999. Min Act: -0.1700
Data Index: 1571780 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7937. Min Range: -3.7937
Max Act: 3.6686. Min Act: -0.1700
Data Index: 6303257 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7937. Min Range: -3.7937
Max Act: 3.6686. Min Act: -0.1700
Data Index: 6395697 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7937. Min Range: -3.7937
Max Act: 3.6686. Min Act: -0.1700
Data Index: 6931054 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7937. Min Range: -3.7937
Max Act: 3.6686. Min Act: -0.1700
Data Index: 4118065 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7937. Min Range: -3.7937
Max Act: 3.6373. Min Act: -0.1700
Data Index: 5324595 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7937. Min Range: -3.7937
Max Act: 3.6373. Min Act: -0.1700
Data Index: 5614029 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7937. Min Range: -3.7937
Max Act: 3.6373. Min Act: -0.1700
Data Index: 6060895 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7937. Min Range: -3.7937
Max Act: 3.6373. Min Act: -0.1700
Data Index: 2272750 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7937. Min Range: -3.7937
Max Act: 3.6373. Min Act: -0.1700
Data Index: 6322563 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7937. Min Range: -3.7937
Max Act: 3.6686. Min Act: -0.1700
Data Index: 809978 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7937. Min Range: -3.7937
Max Act: 3.6373. Min Act: -0.1700
Data Index: 6873128 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7937. Min Range: -3.7937
Max Act: 3.6373. Min Act: -0.1700
Data Index: 370524 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7937. Min Range: -3.7937
Max Act: 3.6373. Min Act: -0.1700
Data Index: 2826514 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19