Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3560 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8698. Min Range: -3.8698
Max Act: 3.8698. Min Act: -0.1700
Data Index: 5758733 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8698. Min Range: -3.8698
Max Act: 3.8385. Min Act: -0.1700
Data Index: 4110298 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8698. Min Range: -3.8698
Max Act: 3.8385. Min Act: -0.1700
Data Index: 5471709 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8698. Min Range: -3.8698
Max Act: 3.8385. Min Act: -0.1700
Data Index: 214136 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8698. Min Range: -3.8698
Max Act: 3.8385. Min Act: -0.1700
Data Index: 5656588 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8698. Min Range: -3.8698
Max Act: 3.8073. Min Act: -0.1700
Data Index: 6943456 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8698. Min Range: -3.8698
Max Act: 3.8073. Min Act: -0.1700
Data Index: 1147805 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8698. Min Range: -3.8698
Max Act: 3.7447. Min Act: -0.1700
Data Index: 6380066 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8698. Min Range: -3.8698
Max Act: 3.7760. Min Act: -0.1700
Data Index: 3853781 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8698. Min Range: -3.8698
Max Act: 3.7447. Min Act: -0.1700
Data Index: 2694361 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8698. Min Range: -3.8698
Max Act: 3.7447. Min Act: -0.1700
Data Index: 2355490 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8698. Min Range: -3.8698
Max Act: 3.7447. Min Act: -0.1700
Data Index: 1840296 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8698. Min Range: -3.8698
Max Act: 3.7134. Min Act: -0.1700
Data Index: 8727721 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8698. Min Range: -3.8698
Max Act: 3.7134. Min Act: -0.1700
Data Index: 4297771 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8698. Min Range: -3.8698
Max Act: 3.6978. Min Act: -0.1700
Data Index: 5847118 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8698. Min Range: -3.8698
Max Act: 3.6821. Min Act: -0.1700
Data Index: 8042783 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8698. Min Range: -3.8698
Max Act: 3.6821. Min Act: -0.1700
Data Index: 5062475 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8698. Min Range: -3.8698
Max Act: 3.6978. Min Act: -0.1700
Data Index: 2198265 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8698. Min Range: -3.8698
Max Act: 3.6978. Min Act: -0.1700
Data Index: 654729 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8698. Min Range: -3.8698
Max Act: 3.6665. Min Act: -0.1700
Data Index: 7862939 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19