Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1933 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8056. Min Range: -6.8056
Max Act: 6.8056. Min Act: -0.1700
Data Index: 888128 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8056. Min Range: -6.8056
Max Act: 6.5556. Min Act: -0.1700
Data Index: 7949361 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8056. Min Range: -6.8056
Max Act: 6.2743. Min Act: -0.1700
Data Index: 8823608 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8056. Min Range: -6.8056
Max Act: 6.2118. Min Act: -0.1700
Data Index: 2489570 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8056. Min Range: -6.8056
Max Act: 6.2118. Min Act: -0.1700
Data Index: 8683297 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8056. Min Range: -6.8056
Max Act: 6.2118. Min Act: -0.1700
Data Index: 7679495 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8056. Min Range: -6.8056
Max Act: 6.1493. Min Act: -0.1700
Data Index: 5081491 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8056. Min Range: -6.8056
Max Act: 6.1493. Min Act: -0.1700
Data Index: 3852533 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8056. Min Range: -6.8056
Max Act: 6.0868. Min Act: -0.1700
Data Index: 804264 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8056. Min Range: -6.8056
Max Act: 6.1493. Min Act: -0.1700
Data Index: 5656748 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8056. Min Range: -6.8056
Max Act: 6.0868. Min Act: -0.1700
Data Index: 4700543 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8056. Min Range: -6.8056
Max Act: 6.1181. Min Act: -0.1700
Data Index: 3566203 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8056. Min Range: -6.8056
Max Act: 6.0868. Min Act: -0.1700
Data Index: 4555596 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8056. Min Range: -6.8056
Max Act: 6.0556. Min Act: -0.1700
Data Index: 255162 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8056. Min Range: -6.8056
Max Act: 6.0556. Min Act: -0.1700
Data Index: 8825212 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8056. Min Range: -6.8056
Max Act: 6.0868. Min Act: -0.1700
Data Index: 524453 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8056. Min Range: -6.8056
Max Act: 6.0868. Min Act: -0.1700
Data Index: 3152066 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8056. Min Range: -6.8056
Max Act: 6.0556. Min Act: -0.1700
Data Index: 7270187 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8056. Min Range: -6.8056
Max Act: 6.0556. Min Act: -0.1700
Data Index: 8585323 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8056. Min Range: -6.8056
Max Act: 6.0243. Min Act: -0.1700
Data Index: 6614342 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #19