Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3059 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0824. Min Range: -4.0824
Max Act: 4.0824. Min Act: -0.1700
Data Index: 7761662 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0824. Min Range: -4.0824
Max Act: 3.9886. Min Act: -0.1700
Data Index: 1788736 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0824. Min Range: -4.0824
Max Act: 3.9261. Min Act: -0.1700
Data Index: 6944301 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0824. Min Range: -4.0824
Max Act: 3.9261. Min Act: -0.1700
Data Index: 5971334 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0824. Min Range: -4.0824
Max Act: 3.8948. Min Act: -0.1700
Data Index: 523388 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0824. Min Range: -4.0824
Max Act: 3.8948. Min Act: -0.1700
Data Index: 6478611 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0824. Min Range: -4.0824
Max Act: 3.8323. Min Act: -0.1700
Data Index: 325394 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0824. Min Range: -4.0824
Max Act: 3.8636. Min Act: -0.1700
Data Index: 1084386 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0824. Min Range: -4.0824
Max Act: 3.8323. Min Act: -0.1700
Data Index: 7342742 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0824. Min Range: -4.0824
Max Act: 3.8323. Min Act: -0.1700
Data Index: 3339831 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0824. Min Range: -4.0824
Max Act: 3.8010. Min Act: -0.1700
Data Index: 1386493 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0824. Min Range: -4.0824
Max Act: 3.8323. Min Act: -0.1700
Data Index: 4979602 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0824. Min Range: -4.0824
Max Act: 3.7698. Min Act: -0.1700
Data Index: 3681412 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0824. Min Range: -4.0824
Max Act: 3.7698. Min Act: -0.1700
Data Index: 2419522 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0824. Min Range: -4.0824
Max Act: 3.7698. Min Act: -0.1700
Data Index: 6756275 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0824. Min Range: -4.0824
Max Act: 3.7385. Min Act: -0.1700
Data Index: 600602 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0824. Min Range: -4.0824
Max Act: 3.7385. Min Act: -0.1700
Data Index: 4149314 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0824. Min Range: -4.0824
Max Act: 3.7385. Min Act: -0.1700
Data Index: 7156330 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0824. Min Range: -4.0824
Max Act: 3.7072. Min Act: -0.1700
Data Index: 5162948 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0824. Min Range: -4.0824
Max Act: 3.7385. Min Act: -0.1700
Data Index: 1251430 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #19