Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 70 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.4950. Min Act: -0.1700
Data Index: 4845319 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.4637. Min Act: -0.1700
Data Index: 8062450 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.3387. Min Act: -0.1700
Data Index: 255803 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.3075. Min Act: -0.1700
Data Index: 1655934 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.2762. Min Act: -0.1700
Data Index: 2627160 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.2137. Min Act: -0.1700
Data Index: 4019114 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.2137. Min Act: -0.1700
Data Index: 7848176 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.2137. Min Act: -0.1700
Data Index: 7761972 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.1825. Min Act: -0.1700
Data Index: 7848178 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.1825. Min Act: -0.1700
Data Index: 7140747 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.1825. Min Act: -0.1700
Data Index: 3194563 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.1825. Min Act: -0.1700
Data Index: 8775905 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.1825. Min Act: -0.1700
Data Index: 3680859 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.1825. Min Act: -0.1700
Data Index: 8104371 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.1512. Min Act: -0.1700
Data Index: 7045974 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.1512. Min Act: -0.1700
Data Index: 1370441 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.1512. Min Act: -0.1700
Data Index: 500853 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.1512. Min Act: -0.1700
Data Index: 4026237 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.1512. Min Act: -0.1700
Data Index: 4264032 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4950. Min Range: -5.4950
Max Act: 5.1512. Min Act: -0.1700
Data Index: 4573086 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #19