Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3376 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1568. Min Range: -7.1568
Max Act: 7.0943. Min Act: -0.1700
Data Index: 6870578 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1568. Min Range: -7.1568
Max Act: 7.1568. Min Act: -0.1700
Data Index: 7986601 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1568. Min Range: -7.1568
Max Act: 6.9693. Min Act: -0.1700
Data Index: 4146614 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1568. Min Range: -7.1568
Max Act: 6.9068. Min Act: -0.1700
Data Index: 7528322 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1568. Min Range: -7.1568
Max Act: 6.8756. Min Act: -0.1700
Data Index: 5491018 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1568. Min Range: -7.1568
Max Act: 6.8443. Min Act: -0.1700
Data Index: 6413088 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1568. Min Range: -7.1568
Max Act: 6.8131. Min Act: -0.1700
Data Index: 2365037 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1568. Min Range: -7.1568
Max Act: 6.8443. Min Act: -0.1700
Data Index: 1318559 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1568. Min Range: -7.1568
Max Act: 6.8131. Min Act: -0.1700
Data Index: 8194607 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1568. Min Range: -7.1568
Max Act: 6.7818. Min Act: -0.1700
Data Index: 2790302 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1568. Min Range: -7.1568
Max Act: 6.7818. Min Act: -0.1700
Data Index: 1403449 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1568. Min Range: -7.1568
Max Act: 6.7506. Min Act: -0.1700
Data Index: 1767614 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1568. Min Range: -7.1568
Max Act: 6.7506. Min Act: -0.1700
Data Index: 5603644 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1568. Min Range: -7.1568
Max Act: 6.7506. Min Act: -0.1700
Data Index: 2790310 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1568. Min Range: -7.1568
Max Act: 6.7193. Min Act: -0.1700
Data Index: 8002659 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1568. Min Range: -7.1568
Max Act: 6.7193. Min Act: -0.1700
Data Index: 2790306 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1568. Min Range: -7.1568
Max Act: 6.7193. Min Act: -0.1700
Data Index: 170040 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1568. Min Range: -7.1568
Max Act: 6.7193. Min Act: -0.1700
Data Index: 6087951 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1568. Min Range: -7.1568
Max Act: 6.7193. Min Act: -0.1700
Data Index: 7825674 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1568. Min Range: -7.1568
Max Act: 6.6881. Min Act: -0.1700
Data Index: 2478715 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19