Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3482 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6739. Min Range: -3.6739
Max Act: 3.6739. Min Act: -0.1700
Data Index: 1366913 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6739. Min Range: -3.6739
Max Act: 3.6426. Min Act: -0.1700
Data Index: 8576120 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6739. Min Range: -3.6739
Max Act: 3.5487. Min Act: -0.1700
Data Index: 3734975 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6739. Min Range: -3.6739
Max Act: 3.5487. Min Act: -0.1700
Data Index: 1127364 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6739. Min Range: -3.6739
Max Act: 3.5487. Min Act: -0.1700
Data Index: 7897009 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6739. Min Range: -3.6739
Max Act: 3.4860. Min Act: -0.1700
Data Index: 8558250 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6739. Min Range: -3.6739
Max Act: 3.4704. Min Act: -0.1700
Data Index: 8050825 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6739. Min Range: -3.6739
Max Act: 3.5017. Min Act: -0.1700
Data Index: 5459500 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6739. Min Range: -3.6739
Max Act: 3.5017. Min Act: -0.1700
Data Index: 1366917 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6739. Min Range: -3.6739
Max Act: 3.4704. Min Act: -0.1700
Data Index: 5749096 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6739. Min Range: -3.6739
Max Act: 3.4390. Min Act: -0.1700
Data Index: 8608513 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6739. Min Range: -3.6739
Max Act: 3.4390. Min Act: -0.1700
Data Index: 2427103 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6739. Min Range: -3.6739
Max Act: 3.4390. Min Act: -0.1700
Data Index: 8830874 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6739. Min Range: -3.6739
Max Act: 3.4234. Min Act: -0.1700
Data Index: 5412590 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6739. Min Range: -3.6739
Max Act: 3.4077. Min Act: -0.1700
Data Index: 1770560 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6739. Min Range: -3.6739
Max Act: 3.4077. Min Act: -0.1700
Data Index: 7507771 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6739. Min Range: -3.6739
Max Act: 3.3763. Min Act: -0.1700
Data Index: 2371513 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6739. Min Range: -3.6739
Max Act: 3.3763. Min Act: -0.1700
Data Index: 5412592 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6739. Min Range: -3.6739
Max Act: 3.3606. Min Act: -0.1700
Data Index: 2067594 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6739. Min Range: -3.6739
Max Act: 3.3606. Min Act: -0.1700
Data Index: 90968 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #19