Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4990 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8725. Min Range: -7.8725
Max Act: 7.8725. Min Act: -0.1700
Data Index: 4858460 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8725. Min Range: -7.8725
Max Act: 7.7787. Min Act: -0.1700
Data Index: 4731562 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8725. Min Range: -7.8725
Max Act: 7.6225. Min Act: -0.1700
Data Index: 3332621 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8725. Min Range: -7.8725
Max Act: 7.5600. Min Act: -0.1700
Data Index: 4728847 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8725. Min Range: -7.8725
Max Act: 7.4975. Min Act: -0.1700
Data Index: 3051050 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8725. Min Range: -7.8725
Max Act: 7.5287. Min Act: -0.1700
Data Index: 2540157 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8725. Min Range: -7.8725
Max Act: 7.4662. Min Act: -0.1700
Data Index: 5278639 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8725. Min Range: -7.8725
Max Act: 7.4662. Min Act: -0.1700
Data Index: 1635915 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8725. Min Range: -7.8725
Max Act: 7.4662. Min Act: -0.1700
Data Index: 2260631 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8725. Min Range: -7.8725
Max Act: 7.4662. Min Act: -0.1700
Data Index: 4284134 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8725. Min Range: -7.8725
Max Act: 7.4037. Min Act: -0.1700
Data Index: 4280119 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8725. Min Range: -7.8725
Max Act: 7.3725. Min Act: -0.1700
Data Index: 8664150 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8725. Min Range: -7.8725
Max Act: 7.3725. Min Act: -0.1700
Data Index: 4227449 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8725. Min Range: -7.8725
Max Act: 7.3412. Min Act: -0.1700
Data Index: 8529399 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8725. Min Range: -7.8725
Max Act: 7.3100. Min Act: -0.1700
Data Index: 217463 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8725. Min Range: -7.8725
Max Act: 7.2787. Min Act: -0.1700
Data Index: 8427784 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8725. Min Range: -7.8725
Max Act: 7.2787. Min Act: -0.1700
Data Index: 156714 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8725. Min Range: -7.8725
Max Act: 7.2787. Min Act: -0.1700
Data Index: 7374056 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8725. Min Range: -7.8725
Max Act: 7.2787. Min Act: -0.1700
Data Index: 6615588 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8725. Min Range: -7.8725
Max Act: 7.2787. Min Act: -0.1700
Data Index: 7327789 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #19