Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4302 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.8652. Min Act: -0.1700
Data Index: 5841997 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.8027. Min Act: -0.1700
Data Index: 5841992 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.8339. Min Act: -0.1700
Data Index: 968730 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.8027. Min Act: -0.1700
Data Index: 5841994 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.8027. Min Act: -0.1700
Data Index: 5841995 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.7714. Min Act: -0.1700
Data Index: 4700624 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.6464. Min Act: -0.1700
Data Index: 5841996 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.5527. Min Act: -0.1700
Data Index: 4730188 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.5527. Min Act: -0.1700
Data Index: 5510754 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.5214. Min Act: -0.1700
Data Index: 7082994 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.4902. Min Act: -0.1700
Data Index: 4814243 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.4902. Min Act: -0.1700
Data Index: 2769622 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.4276. Min Act: -0.1700
Data Index: 4539634 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.3964. Min Act: -0.1700
Data Index: 2011001 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.3651. Min Act: -0.1700
Data Index: 5304651 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.3964. Min Act: -0.1700
Data Index: 1212673 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.3339. Min Act: -0.1700
Data Index: 4525717 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.3339. Min Act: -0.1700
Data Index: 8339356 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.3339. Min Act: -0.1700
Data Index: 3261032 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.2714. Min Act: -0.1700
Data Index: 6595257 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19