Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5142 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.9313. Min Act: -0.1700
Data Index: 465488 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.8063. Min Act: -0.1700
Data Index: 6796139 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.7438. Min Act: -0.1700
Data Index: 494129 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.7438. Min Act: -0.1700
Data Index: 3643478 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.7125. Min Act: -0.1700
Data Index: 6390270 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.7438. Min Act: -0.1700
Data Index: 5625578 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.6813. Min Act: -0.1700
Data Index: 4939803 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.6500. Min Act: -0.1700
Data Index: 3680471 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.7125. Min Act: -0.1700
Data Index: 287940 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.6500. Min Act: -0.1700
Data Index: 4504068 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.6500. Min Act: -0.1700
Data Index: 8366062 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.6500. Min Act: -0.1700
Data Index: 7668825 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.6500. Min Act: -0.1700
Data Index: 1864838 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.5875. Min Act: -0.1700
Data Index: 7003440 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.6188. Min Act: -0.1700
Data Index: 2649176 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.5563. Min Act: -0.1700
Data Index: 4637668 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.5250. Min Act: -0.1700
Data Index: 2785907 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.5563. Min Act: -0.1700
Data Index: 5025404 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.5563. Min Act: -0.1700
Data Index: 1007779 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.5563. Min Act: -0.1700
Data Index: 5876487 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #19