Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3281 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.7040. Min Act: -0.1700
Data Index: 2939644 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.5790. Min Act: -0.1700
Data Index: 2023547 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.4852. Min Act: -0.1700
Data Index: 7692465 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.4540. Min Act: -0.1700
Data Index: 8352855 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.4540. Min Act: -0.1700
Data Index: 528321 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.4227. Min Act: -0.1700
Data Index: 6884003 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.4227. Min Act: -0.1700
Data Index: 6741147 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.3915. Min Act: -0.1700
Data Index: 5561526 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.3915. Min Act: -0.1700
Data Index: 4839326 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.3915. Min Act: -0.1700
Data Index: 2229035 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.3915. Min Act: -0.1700
Data Index: 4851180 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.4227. Min Act: -0.1700
Data Index: 1638459 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.3915. Min Act: -0.1700
Data Index: 7744305 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.3915. Min Act: -0.1700
Data Index: 325093 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.3602. Min Act: -0.1700
Data Index: 217672 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.3602. Min Act: -0.1700
Data Index: 7148828 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.2977. Min Act: -0.1700
Data Index: 7965493 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.3290. Min Act: -0.1700
Data Index: 5725148 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.3290. Min Act: -0.1700
Data Index: 3939164 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.3290. Min Act: -0.1700
Data Index: 290480 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19