Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3382 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9734. Min Range: -6.9734
Max Act: 6.9734. Min Act: -0.1700
Data Index: 3017370 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9734. Min Range: -6.9734
Max Act: 6.9422. Min Act: -0.1700
Data Index: 4524549 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9734. Min Range: -6.9734
Max Act: 6.9109. Min Act: -0.1700
Data Index: 6037665 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9734. Min Range: -6.9734
Max Act: 6.8484. Min Act: -0.1700
Data Index: 3720616 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9734. Min Range: -6.9734
Max Act: 6.7859. Min Act: -0.1700
Data Index: 793712 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9734. Min Range: -6.9734
Max Act: 6.7859. Min Act: -0.1700
Data Index: 378663 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9734. Min Range: -6.9734
Max Act: 6.7547. Min Act: -0.1700
Data Index: 3151665 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9734. Min Range: -6.9734
Max Act: 6.6922. Min Act: -0.1700
Data Index: 5010993 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9734. Min Range: -6.9734
Max Act: 6.6922. Min Act: -0.1700
Data Index: 6156660 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9734. Min Range: -6.9734
Max Act: 6.6297. Min Act: -0.1700
Data Index: 5132251 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9734. Min Range: -6.9734
Max Act: 6.6609. Min Act: -0.1700
Data Index: 7850769 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9734. Min Range: -6.9734
Max Act: 6.6609. Min Act: -0.1700
Data Index: 7037210 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9734. Min Range: -6.9734
Max Act: 6.6297. Min Act: -0.1700
Data Index: 7619247 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9734. Min Range: -6.9734
Max Act: 6.6609. Min Act: -0.1700
Data Index: 2981518 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9734. Min Range: -6.9734
Max Act: 6.5984. Min Act: -0.1700
Data Index: 54487 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9734. Min Range: -6.9734
Max Act: 6.5984. Min Act: -0.1700
Data Index: 6789093 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9734. Min Range: -6.9734
Max Act: 6.5984. Min Act: -0.1700
Data Index: 2603340 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9734. Min Range: -6.9734
Max Act: 6.5672. Min Act: -0.1700
Data Index: 2846618 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9734. Min Range: -6.9734
Max Act: 6.5672. Min Act: -0.1700
Data Index: 4318720 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9734. Min Range: -6.9734
Max Act: 6.5672. Min Act: -0.1700
Data Index: 7146317 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19