Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 109 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9394. Min Range: -7.9394
Max Act: 7.9394. Min Act: -0.1700
Data Index: 4755856 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9394. Min Range: -7.9394
Max Act: 7.6269. Min Act: -0.1700
Data Index: 8289561 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9394. Min Range: -7.9394
Max Act: 7.4394. Min Act: -0.1700
Data Index: 5498082 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9394. Min Range: -7.9394
Max Act: 7.2831. Min Act: -0.1700
Data Index: 5973305 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9394. Min Range: -7.9394
Max Act: 7.1581. Min Act: -0.1700
Data Index: 5494422 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9394. Min Range: -7.9394
Max Act: 7.1269. Min Act: -0.1700
Data Index: 6519610 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9394. Min Range: -7.9394
Max Act: 7.1269. Min Act: -0.1700
Data Index: 8057920 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9394. Min Range: -7.9394
Max Act: 7.1269. Min Act: -0.1700
Data Index: 117874 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9394. Min Range: -7.9394
Max Act: 7.0644. Min Act: -0.1700
Data Index: 498723 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9394. Min Range: -7.9394
Max Act: 7.0331. Min Act: -0.1700
Data Index: 2250350 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9394. Min Range: -7.9394
Max Act: 7.0331. Min Act: -0.1700
Data Index: 5189357 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9394. Min Range: -7.9394
Max Act: 7.0331. Min Act: -0.1700
Data Index: 7657038 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9394. Min Range: -7.9394
Max Act: 7.0019. Min Act: -0.1700
Data Index: 60923 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9394. Min Range: -7.9394
Max Act: 6.9706. Min Act: -0.1700
Data Index: 5342009 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9394. Min Range: -7.9394
Max Act: 7.0019. Min Act: -0.1700
Data Index: 4392967 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9394. Min Range: -7.9394
Max Act: 6.9394. Min Act: -0.1700
Data Index: 8713765 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9394. Min Range: -7.9394
Max Act: 6.9394. Min Act: -0.1700
Data Index: 5802821 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9394. Min Range: -7.9394
Max Act: 6.9394. Min Act: -0.1700
Data Index: 3669929 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9394. Min Range: -7.9394
Max Act: 6.9394. Min Act: -0.1700
Data Index: 1769591 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9394. Min Range: -7.9394
Max Act: 6.9394. Min Act: -0.1700
Data Index: 4331515 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #19