Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3964 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1484. Min Range: -5.1484
Max Act: 5.1484. Min Act: -0.1700
Data Index: 6623858 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1484. Min Range: -5.1484
Max Act: 5.0859. Min Act: -0.1700
Data Index: 4733684 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1484. Min Range: -5.1484
Max Act: 5.0546. Min Act: -0.1700
Data Index: 1976069 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1484. Min Range: -5.1484
Max Act: 5.0546. Min Act: -0.1700
Data Index: 1124041 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1484. Min Range: -5.1484
Max Act: 5.0234. Min Act: -0.1700
Data Index: 7065921 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1484. Min Range: -5.1484
Max Act: 5.0234. Min Act: -0.1700
Data Index: 3822467 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1484. Min Range: -5.1484
Max Act: 4.9921. Min Act: -0.1700
Data Index: 2864413 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1484. Min Range: -5.1484
Max Act: 4.9609. Min Act: -0.1700
Data Index: 792750 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1484. Min Range: -5.1484
Max Act: 4.9609. Min Act: -0.1700
Data Index: 7871239 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1484. Min Range: -5.1484
Max Act: 4.9296. Min Act: -0.1700
Data Index: 4791402 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1484. Min Range: -5.1484
Max Act: 4.8984. Min Act: -0.1700
Data Index: 1461498 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1484. Min Range: -5.1484
Max Act: 4.9296. Min Act: -0.1700
Data Index: 2830268 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1484. Min Range: -5.1484
Max Act: 4.9296. Min Act: -0.1700
Data Index: 5397841 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1484. Min Range: -5.1484
Max Act: 4.8984. Min Act: -0.1700
Data Index: 4972328 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1484. Min Range: -5.1484
Max Act: 4.9296. Min Act: -0.1700
Data Index: 5458899 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1484. Min Range: -5.1484
Max Act: 4.9296. Min Act: -0.1700
Data Index: 7525511 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1484. Min Range: -5.1484
Max Act: 4.8984. Min Act: -0.1700
Data Index: 1768946 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1484. Min Range: -5.1484
Max Act: 4.8671. Min Act: -0.1700
Data Index: 8008588 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1484. Min Range: -5.1484
Max Act: 4.8984. Min Act: -0.1700
Data Index: 8397415 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1484. Min Range: -5.1484
Max Act: 4.8671. Min Act: -0.1700
Data Index: 2250152 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #19