Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3685 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4502. Min Range: -6.4502
Max Act: 6.4502. Min Act: -0.1700
Data Index: 4121480 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4502. Min Range: -6.4502
Max Act: 6.2939. Min Act: -0.1700
Data Index: 2267127 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4502. Min Range: -6.4502
Max Act: 6.1377. Min Act: -0.1700
Data Index: 1020518 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4502. Min Range: -6.4502
Max Act: 6.1064. Min Act: -0.1700
Data Index: 8607514 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4502. Min Range: -6.4502
Max Act: 6.0439. Min Act: -0.1700
Data Index: 4255587 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4502. Min Range: -6.4502
Max Act: 6.0439. Min Act: -0.1700
Data Index: 4673392 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4502. Min Range: -6.4502
Max Act: 5.9502. Min Act: -0.1700
Data Index: 5515087 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4502. Min Range: -6.4502
Max Act: 5.9502. Min Act: -0.1700
Data Index: 4799924 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4502. Min Range: -6.4502
Max Act: 5.9502. Min Act: -0.1700
Data Index: 3956070 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4502. Min Range: -6.4502
Max Act: 5.9502. Min Act: -0.1700
Data Index: 5037898 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4502. Min Range: -6.4502
Max Act: 5.9502. Min Act: -0.1700
Data Index: 5744730 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4502. Min Range: -6.4502
Max Act: 5.9502. Min Act: -0.1700
Data Index: 4751868 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4502. Min Range: -6.4502
Max Act: 5.9189. Min Act: -0.1700
Data Index: 5679902 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4502. Min Range: -6.4502
Max Act: 5.9189. Min Act: -0.1700
Data Index: 882497 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4502. Min Range: -6.4502
Max Act: 5.9189. Min Act: -0.1700
Data Index: 2715820 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4502. Min Range: -6.4502
Max Act: 5.9189. Min Act: -0.1700
Data Index: 5275469 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4502. Min Range: -6.4502
Max Act: 5.8877. Min Act: -0.1700
Data Index: 6422142 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4502. Min Range: -6.4502
Max Act: 5.8877. Min Act: -0.1700
Data Index: 2922510 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4502. Min Range: -6.4502
Max Act: 5.9189. Min Act: -0.1700
Data Index: 1324263 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4502. Min Range: -6.4502
Max Act: 5.8877. Min Act: -0.1700
Data Index: 7819972 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19