Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3389 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5715. Min Range: -7.5715
Max Act: 7.5715. Min Act: -0.1700
Data Index: 8821195 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5715. Min Range: -7.5715
Max Act: 7.2278. Min Act: -0.1700
Data Index: 8280404 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5715. Min Range: -7.5715
Max Act: 6.9778. Min Act: -0.1700
Data Index: 122135 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5715. Min Range: -7.5715
Max Act: 6.9778. Min Act: -0.1700
Data Index: 7932073 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5715. Min Range: -7.5715
Max Act: 6.8528. Min Act: -0.1700
Data Index: 6699534 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5715. Min Range: -7.5715
Max Act: 6.6965. Min Act: -0.1700
Data Index: 4074013 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5715. Min Range: -7.5715
Max Act: 6.6653. Min Act: -0.1700
Data Index: 4285531 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5715. Min Range: -7.5715
Max Act: 6.6653. Min Act: -0.1700
Data Index: 5904914 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5715. Min Range: -7.5715
Max Act: 6.6653. Min Act: -0.1700
Data Index: 8176476 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5715. Min Range: -7.5715
Max Act: 6.6653. Min Act: -0.1700
Data Index: 1589253 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5715. Min Range: -7.5715
Max Act: 6.6028. Min Act: -0.1700
Data Index: 4892346 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5715. Min Range: -7.5715
Max Act: 6.6028. Min Act: -0.1700
Data Index: 6463509 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5715. Min Range: -7.5715
Max Act: 6.6028. Min Act: -0.1700
Data Index: 5986162 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5715. Min Range: -7.5715
Max Act: 6.5715. Min Act: -0.1700
Data Index: 8572115 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5715. Min Range: -7.5715
Max Act: 6.5715. Min Act: -0.1700
Data Index: 5483449 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5715. Min Range: -7.5715
Max Act: 6.5715. Min Act: -0.1700
Data Index: 1921984 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5715. Min Range: -7.5715
Max Act: 6.5403. Min Act: -0.1700
Data Index: 6918816 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5715. Min Range: -7.5715
Max Act: 6.5403. Min Act: -0.1700
Data Index: 2497348 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5715. Min Range: -7.5715
Max Act: 6.5403. Min Act: -0.1700
Data Index: 3091328 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5715. Min Range: -7.5715
Max Act: 6.5090. Min Act: -0.1700
Data Index: 5790519 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19