Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1757 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.9792. Min Act: -0.1700
Data Index: 6244211 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.9792. Min Act: -0.1700
Data Index: 4138405 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.9480. Min Act: -0.1700
Data Index: 8450833 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.9480. Min Act: -0.1700
Data Index: 6324702 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.9480. Min Act: -0.1700
Data Index: 7013557 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.9167. Min Act: -0.1700
Data Index: 559020 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.9167. Min Act: -0.1700
Data Index: 4645696 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.9167. Min Act: -0.1700
Data Index: 7432474 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.8854. Min Act: -0.1700
Data Index: 1240052 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.8854. Min Act: -0.1700
Data Index: 3391792 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.8854. Min Act: -0.1700
Data Index: 5038695 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.8854. Min Act: -0.1700
Data Index: 6205313 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.8854. Min Act: -0.1700
Data Index: 2429329 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.8542. Min Act: -0.1700
Data Index: 5009286 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.8542. Min Act: -0.1700
Data Index: 7459940 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.8229. Min Act: -0.1700
Data Index: 7072179 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.8229. Min Act: -0.1700
Data Index: 5525965 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.8229. Min Act: -0.1700
Data Index: 2068275 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.8229. Min Act: -0.1700
Data Index: 7576999 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.8229. Min Act: -0.1700
Data Index: 6460702 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19