Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3322 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0756. Min Range: -6.0756
Max Act: 6.0756. Min Act: -0.1700
Data Index: 5199504 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0756. Min Range: -6.0756
Max Act: 5.8568. Min Act: -0.1700
Data Index: 7804831 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0756. Min Range: -6.0756
Max Act: 5.7943. Min Act: -0.1700
Data Index: 2685240 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0756. Min Range: -6.0756
Max Act: 5.7943. Min Act: -0.1700
Data Index: 2441036 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0756. Min Range: -6.0756
Max Act: 5.7943. Min Act: -0.1700
Data Index: 7145948 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0756. Min Range: -6.0756
Max Act: 5.7631. Min Act: -0.1700
Data Index: 5006529 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0756. Min Range: -6.0756
Max Act: 5.7318. Min Act: -0.1700
Data Index: 2238566 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0756. Min Range: -6.0756
Max Act: 5.7318. Min Act: -0.1700
Data Index: 7067503 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0756. Min Range: -6.0756
Max Act: 5.7006. Min Act: -0.1700
Data Index: 4176359 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0756. Min Range: -6.0756
Max Act: 5.6693. Min Act: -0.1700
Data Index: 4863502 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0756. Min Range: -6.0756
Max Act: 5.6381. Min Act: -0.1700
Data Index: 5025078 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0756. Min Range: -6.0756
Max Act: 5.6068. Min Act: -0.1700
Data Index: 5665275 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0756. Min Range: -6.0756
Max Act: 5.6068. Min Act: -0.1700
Data Index: 6549329 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0756. Min Range: -6.0756
Max Act: 5.6068. Min Act: -0.1700
Data Index: 1060991 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0756. Min Range: -6.0756
Max Act: 5.6068. Min Act: -0.1700
Data Index: 4032767 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0756. Min Range: -6.0756
Max Act: 5.5756. Min Act: -0.1700
Data Index: 8457622 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0756. Min Range: -6.0756
Max Act: 5.5756. Min Act: -0.1700
Data Index: 3413654 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0756. Min Range: -6.0756
Max Act: 5.5443. Min Act: -0.1700
Data Index: 6041927 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0756. Min Range: -6.0756
Max Act: 5.5756. Min Act: -0.1700
Data Index: 1278165 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0756. Min Range: -6.0756
Max Act: 5.5443. Min Act: -0.1700
Data Index: 6330304 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19