Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3500 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7753. Min Range: -2.7753
Max Act: 2.7753. Min Act: -0.1700
Data Index: 2653122 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7753. Min Range: -2.7753
Max Act: 2.6795. Min Act: -0.1700
Data Index: 4454956 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7753. Min Range: -2.7753
Max Act: 2.6634. Min Act: -0.1700
Data Index: 817003 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7753. Min Range: -2.7753
Max Act: 2.6474. Min Act: -0.1700
Data Index: 2871521 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7753. Min Range: -2.7753
Max Act: 2.6474. Min Act: -0.1700
Data Index: 6993361 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7753. Min Range: -2.7753
Max Act: 2.5992. Min Act: -0.1700
Data Index: 5972506 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7753. Min Range: -2.7753
Max Act: 2.6153. Min Act: -0.1700
Data Index: 6084281 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7753. Min Range: -2.7753
Max Act: 2.5992. Min Act: -0.1700
Data Index: 5343208 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7753. Min Range: -2.7753
Max Act: 2.5831. Min Act: -0.1700
Data Index: 3633191 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7753. Min Range: -2.7753
Max Act: 2.6153. Min Act: -0.1700
Data Index: 729043 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7753. Min Range: -2.7753
Max Act: 2.5670. Min Act: -0.1700
Data Index: 310567 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7753. Min Range: -2.7753
Max Act: 2.5670. Min Act: -0.1700
Data Index: 488190 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7753. Min Range: -2.7753
Max Act: 2.5831. Min Act: -0.1700
Data Index: 2261525 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7753. Min Range: -2.7753
Max Act: 2.5831. Min Act: -0.1700
Data Index: 4227298 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7753. Min Range: -2.7753
Max Act: 2.5831. Min Act: -0.1700
Data Index: 4693646 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7753. Min Range: -2.7753
Max Act: 2.5670. Min Act: -0.1700
Data Index: 7710008 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7753. Min Range: -2.7753
Max Act: 2.5670. Min Act: -0.1700
Data Index: 4438399 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7753. Min Range: -2.7753
Max Act: 2.5670. Min Act: -0.1700
Data Index: 6531227 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7753. Min Range: -2.7753
Max Act: 2.5347. Min Act: -0.1700
Data Index: 1288237 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7753. Min Range: -2.7753
Max Act: 2.5508. Min Act: -0.1700
Data Index: 4025608 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #19