Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5775 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4693. Min Range: -8.4693
Max Act: 8.4693. Min Act: -0.1700
Data Index: 8373939 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4693. Min Range: -8.4693
Max Act: 8.3443. Min Act: -0.1700
Data Index: 6793832 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4693. Min Range: -8.4693
Max Act: 8.1568. Min Act: -0.1700
Data Index: 2392026 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4693. Min Range: -8.4693
Max Act: 7.8756. Min Act: -0.1700
Data Index: 8430981 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4693. Min Range: -8.4693
Max Act: 7.9068. Min Act: -0.1700
Data Index: 950471 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4693. Min Range: -8.4693
Max Act: 7.8131. Min Act: -0.1700
Data Index: 2881703 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4693. Min Range: -8.4693
Max Act: 7.7506. Min Act: -0.1700
Data Index: 1490746 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4693. Min Range: -8.4693
Max Act: 7.6881. Min Act: -0.1700
Data Index: 6126113 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4693. Min Range: -8.4693
Max Act: 7.6568. Min Act: -0.1700
Data Index: 493828 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4693. Min Range: -8.4693
Max Act: 7.6256. Min Act: -0.1700
Data Index: 839264 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4693. Min Range: -8.4693
Max Act: 7.6568. Min Act: -0.1700
Data Index: 8034458 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4693. Min Range: -8.4693
Max Act: 7.5943. Min Act: -0.1700
Data Index: 6647341 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4693. Min Range: -8.4693
Max Act: 7.5943. Min Act: -0.1700
Data Index: 2243148 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4693. Min Range: -8.4693
Max Act: 7.5006. Min Act: -0.1700
Data Index: 1459303 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4693. Min Range: -8.4693
Max Act: 7.4381. Min Act: -0.1700
Data Index: 6933393 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4693. Min Range: -8.4693
Max Act: 7.4381. Min Act: -0.1700
Data Index: 6587416 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4693. Min Range: -8.4693
Max Act: 7.4381. Min Act: -0.1700
Data Index: 4307656 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4693. Min Range: -8.4693
Max Act: 7.4068. Min Act: -0.1700
Data Index: 1482148 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4693. Min Range: -8.4693
Max Act: 7.3756. Min Act: -0.1700
Data Index: 5963769 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4693. Min Range: -8.4693
Max Act: 7.4068. Min Act: -0.1700
Data Index: 7196687 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19