Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1033 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8934. Min Range: -6.8934
Max Act: 6.8934. Min Act: -0.1700
Data Index: 4219310 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8934. Min Range: -6.8934
Max Act: 6.8622. Min Act: -0.1700
Data Index: 1346973 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8934. Min Range: -6.8934
Max Act: 6.7372. Min Act: -0.1700
Data Index: 3506314 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8934. Min Range: -6.8934
Max Act: 6.6122. Min Act: -0.1700
Data Index: 294972 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8934. Min Range: -6.8934
Max Act: 6.5497. Min Act: -0.1700
Data Index: 7105895 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8934. Min Range: -6.8934
Max Act: 6.5497. Min Act: -0.1700
Data Index: 2951799 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8934. Min Range: -6.8934
Max Act: 6.5184. Min Act: -0.1700
Data Index: 5476074 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8934. Min Range: -6.8934
Max Act: 6.4559. Min Act: -0.1700
Data Index: 1516743 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8934. Min Range: -6.8934
Max Act: 6.4247. Min Act: -0.1700
Data Index: 900635 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8934. Min Range: -6.8934
Max Act: 6.4559. Min Act: -0.1700
Data Index: 6441832 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8934. Min Range: -6.8934
Max Act: 6.4247. Min Act: -0.1700
Data Index: 7182820 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8934. Min Range: -6.8934
Max Act: 6.3934. Min Act: -0.1700
Data Index: 8320023 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8934. Min Range: -6.8934
Max Act: 6.3622. Min Act: -0.1700
Data Index: 198308 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8934. Min Range: -6.8934
Max Act: 6.2684. Min Act: -0.1700
Data Index: 4832521 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8934. Min Range: -6.8934
Max Act: 6.2684. Min Act: -0.1700
Data Index: 1149131 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8934. Min Range: -6.8934
Max Act: 6.2684. Min Act: -0.1700
Data Index: 1284767 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8934. Min Range: -6.8934
Max Act: 6.2684. Min Act: -0.1700
Data Index: 7676146 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8934. Min Range: -6.8934
Max Act: 6.2684. Min Act: -0.1700
Data Index: 6351584 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8934. Min Range: -6.8934
Max Act: 6.2372. Min Act: -0.1700
Data Index: 7750234 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8934. Min Range: -6.8934
Max Act: 6.2372. Min Act: -0.1700
Data Index: 4242272 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #19