Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2557 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9797. Min Range: -4.9797
Max Act: 4.9797. Min Act: -0.1700
Data Index: 2808738 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9797. Min Range: -4.9797
Max Act: 4.9484. Min Act: -0.1700
Data Index: 2952935 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9797. Min Range: -4.9797
Max Act: 4.9484. Min Act: -0.1700
Data Index: 566107 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9797. Min Range: -4.9797
Max Act: 4.9172. Min Act: -0.1700
Data Index: 3689705 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9797. Min Range: -4.9797
Max Act: 4.9172. Min Act: -0.1700
Data Index: 1585203 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9797. Min Range: -4.9797
Max Act: 4.8859. Min Act: -0.1700
Data Index: 6980486 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9797. Min Range: -4.9797
Max Act: 4.8859. Min Act: -0.1700
Data Index: 1631603 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9797. Min Range: -4.9797
Max Act: 4.9172. Min Act: -0.1700
Data Index: 1796386 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9797. Min Range: -4.9797
Max Act: 4.8859. Min Act: -0.1700
Data Index: 5071319 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9797. Min Range: -4.9797
Max Act: 4.8547. Min Act: -0.1700
Data Index: 4109858 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9797. Min Range: -4.9797
Max Act: 4.8547. Min Act: -0.1700
Data Index: 7148749 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9797. Min Range: -4.9797
Max Act: 4.8547. Min Act: -0.1700
Data Index: 6580348 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9797. Min Range: -4.9797
Max Act: 4.8547. Min Act: -0.1700
Data Index: 5882845 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9797. Min Range: -4.9797
Max Act: 4.8547. Min Act: -0.1700
Data Index: 5395085 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9797. Min Range: -4.9797
Max Act: 4.8547. Min Act: -0.1700
Data Index: 2210811 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9797. Min Range: -4.9797
Max Act: 4.8547. Min Act: -0.1700
Data Index: 988059 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9797. Min Range: -4.9797
Max Act: 4.8547. Min Act: -0.1700
Data Index: 2085452 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9797. Min Range: -4.9797
Max Act: 4.8547. Min Act: -0.1700
Data Index: 1914051 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9797. Min Range: -4.9797
Max Act: 4.8547. Min Act: -0.1700
Data Index: 3406552 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9797. Min Range: -4.9797
Max Act: 4.8547. Min Act: -0.1700
Data Index: 3378909 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #19