Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4602 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3498. Min Range: -5.3498
Max Act: 5.3498. Min Act: -0.1700
Data Index: 5185670 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3498. Min Range: -5.3498
Max Act: 5.0686. Min Act: -0.1700
Data Index: 1964889 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3498. Min Range: -5.3498
Max Act: 5.0998. Min Act: -0.1700
Data Index: 8422408 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3498. Min Range: -5.3498
Max Act: 5.0686. Min Act: -0.1700
Data Index: 5677727 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3498. Min Range: -5.3498
Max Act: 5.0686. Min Act: -0.1700
Data Index: 991869 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3498. Min Range: -5.3498
Max Act: 5.0686. Min Act: -0.1700
Data Index: 7999012 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3498. Min Range: -5.3498
Max Act: 5.0373. Min Act: -0.1700
Data Index: 3165903 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3498. Min Range: -5.3498
Max Act: 5.0373. Min Act: -0.1700
Data Index: 1031099 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3498. Min Range: -5.3498
Max Act: 5.0373. Min Act: -0.1700
Data Index: 8001565 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3498. Min Range: -5.3498
Max Act: 5.0061. Min Act: -0.1700
Data Index: 6327480 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3498. Min Range: -5.3498
Max Act: 5.0061. Min Act: -0.1700
Data Index: 3186150 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3498. Min Range: -5.3498
Max Act: 5.0061. Min Act: -0.1700
Data Index: 2089470 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3498. Min Range: -5.3498
Max Act: 4.9748. Min Act: -0.1700
Data Index: 1478108 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3498. Min Range: -5.3498
Max Act: 4.9748. Min Act: -0.1700
Data Index: 2261941 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3498. Min Range: -5.3498
Max Act: 4.9748. Min Act: -0.1700
Data Index: 2478912 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3498. Min Range: -5.3498
Max Act: 4.9748. Min Act: -0.1700
Data Index: 2437020 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3498. Min Range: -5.3498
Max Act: 4.9436. Min Act: -0.1700
Data Index: 5633239 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3498. Min Range: -5.3498
Max Act: 4.9436. Min Act: -0.1700
Data Index: 7823055 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3498. Min Range: -5.3498
Max Act: 4.9748. Min Act: -0.1700
Data Index: 5942862 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3498. Min Range: -5.3498
Max Act: 4.9436. Min Act: -0.1700
Data Index: 2530880 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19