Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2897 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4919. Min Range: -5.4919
Max Act: 5.4919. Min Act: -0.1700
Data Index: 806148 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4919. Min Range: -5.4919
Max Act: 5.4294. Min Act: -0.1700
Data Index: 7806227 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4919. Min Range: -5.4919
Max Act: 5.3982. Min Act: -0.1700
Data Index: 1795891 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4919. Min Range: -5.4919
Max Act: 5.3357. Min Act: -0.1700
Data Index: 2438248 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4919. Min Range: -5.4919
Max Act: 5.1794. Min Act: -0.1700
Data Index: 806149 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4919. Min Range: -5.4919
Max Act: 5.1794. Min Act: -0.1700
Data Index: 1995595 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4919. Min Range: -5.4919
Max Act: 5.1482. Min Act: -0.1700
Data Index: 6908060 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4919. Min Range: -5.4919
Max Act: 5.1169. Min Act: -0.1700
Data Index: 3786224 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4919. Min Range: -5.4919
Max Act: 5.1169. Min Act: -0.1700
Data Index: 1245741 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4919. Min Range: -5.4919
Max Act: 5.1169. Min Act: -0.1700
Data Index: 1995590 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4919. Min Range: -5.4919
Max Act: 5.1169. Min Act: -0.1700
Data Index: 113679 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4919. Min Range: -5.4919
Max Act: 5.0857. Min Act: -0.1700
Data Index: 6506147 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4919. Min Range: -5.4919
Max Act: 5.0857. Min Act: -0.1700
Data Index: 237836 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4919. Min Range: -5.4919
Max Act: 5.0544. Min Act: -0.1700
Data Index: 5159850 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4919. Min Range: -5.4919
Max Act: 4.9919. Min Act: -0.1699
Data Index: 5858655 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4919. Min Range: -5.4919
Max Act: 4.9919. Min Act: -0.1700
Data Index: 4803592 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4919. Min Range: -5.4919
Max Act: 4.9919. Min Act: -0.1700
Data Index: 4492123 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4919. Min Range: -5.4919
Max Act: 4.9919. Min Act: -0.1700
Data Index: 5183367 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4919. Min Range: -5.4919
Max Act: 4.9919. Min Act: -0.1700
Data Index: 8068735 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4919. Min Range: -5.4919
Max Act: 4.9607. Min Act: -0.1700
Data Index: 1520956 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19