Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3645 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1063. Min Range: -7.1063
Max Act: 7.1063. Min Act: -0.1700
Data Index: 8063592 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1063. Min Range: -7.1063
Max Act: 6.8563. Min Act: -0.1700
Data Index: 4729436 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1063. Min Range: -7.1063
Max Act: 6.8251. Min Act: -0.1700
Data Index: 7961158 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1063. Min Range: -7.1063
Max Act: 6.8251. Min Act: -0.1700
Data Index: 7748367 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1063. Min Range: -7.1063
Max Act: 6.7626. Min Act: -0.1700
Data Index: 6155531 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1063. Min Range: -7.1063
Max Act: 6.7626. Min Act: -0.1700
Data Index: 2906965 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1063. Min Range: -7.1063
Max Act: 6.7313. Min Act: -0.1700
Data Index: 1279457 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1063. Min Range: -7.1063
Max Act: 6.7313. Min Act: -0.1700
Data Index: 7607485 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1063. Min Range: -7.1063
Max Act: 6.6688. Min Act: -0.1700
Data Index: 8441982 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1063. Min Range: -7.1063
Max Act: 6.6376. Min Act: -0.1700
Data Index: 1329075 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1063. Min Range: -7.1063
Max Act: 6.6376. Min Act: -0.1700
Data Index: 8634416 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1063. Min Range: -7.1063
Max Act: 6.6063. Min Act: -0.1700
Data Index: 5460662 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1063. Min Range: -7.1063
Max Act: 6.6063. Min Act: -0.1700
Data Index: 6283204 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1063. Min Range: -7.1063
Max Act: 6.6376. Min Act: -0.1700
Data Index: 4905658 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1063. Min Range: -7.1063
Max Act: 6.6063. Min Act: -0.1700
Data Index: 4905657 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1063. Min Range: -7.1063
Max Act: 6.5751. Min Act: -0.1700
Data Index: 5206124 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1063. Min Range: -7.1063
Max Act: 6.5751. Min Act: -0.1700
Data Index: 2070792 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1063. Min Range: -7.1063
Max Act: 6.5751. Min Act: -0.1700
Data Index: 4814490 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1063. Min Range: -7.1063
Max Act: 6.5751. Min Act: -0.1700
Data Index: 6848738 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1063. Min Range: -7.1063
Max Act: 6.5751. Min Act: -0.1700
Data Index: 8002112 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19