Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3059 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0948. Min Range: -4.0948
Max Act: 4.0948. Min Act: -0.1700
Data Index: 1226420 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0948. Min Range: -4.0948
Max Act: 4.0635. Min Act: -0.1700
Data Index: 2683441 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0948. Min Range: -4.0948
Max Act: 4.0322. Min Act: -0.1700
Data Index: 3458888 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0948. Min Range: -4.0948
Max Act: 4.0010. Min Act: -0.1700
Data Index: 7776549 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0948. Min Range: -4.0948
Max Act: 4.0010. Min Act: -0.1700
Data Index: 2479769 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0948. Min Range: -4.0948
Max Act: 3.9385. Min Act: -0.1700
Data Index: 4309105 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0948. Min Range: -4.0948
Max Act: 3.9385. Min Act: -0.1700
Data Index: 4919983 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0948. Min Range: -4.0948
Max Act: 3.9072. Min Act: -0.1700
Data Index: 4196240 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0948. Min Range: -4.0948
Max Act: 3.9385. Min Act: -0.1700
Data Index: 3342119 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0948. Min Range: -4.0948
Max Act: 3.9072. Min Act: -0.1700
Data Index: 4309099 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0948. Min Range: -4.0948
Max Act: 3.9072. Min Act: -0.1700
Data Index: 1604210 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0948. Min Range: -4.0948
Max Act: 3.9072. Min Act: -0.1700
Data Index: 2682254 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0948. Min Range: -4.0948
Max Act: 3.9072. Min Act: -0.1700
Data Index: 3500137 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0948. Min Range: -4.0948
Max Act: 3.9072. Min Act: -0.1700
Data Index: 7095764 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0948. Min Range: -4.0948
Max Act: 3.8759. Min Act: -0.1700
Data Index: 8476825 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0948. Min Range: -4.0948
Max Act: 3.8447. Min Act: -0.1700
Data Index: 2759678 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0948. Min Range: -4.0948
Max Act: 3.8134. Min Act: -0.1700
Data Index: 1657848 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0948. Min Range: -4.0948
Max Act: 3.8447. Min Act: -0.1700
Data Index: 4911938 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0948. Min Range: -4.0948
Max Act: 3.8447. Min Act: -0.1700
Data Index: 5586352 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0948. Min Range: -4.0948
Max Act: 3.8447. Min Act: -0.1700
Data Index: 3651077 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19