Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4648 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3055. Min Range: -5.3055
Max Act: 5.3055. Min Act: -0.1700
Data Index: 1970527 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3055. Min Range: -5.3055
Max Act: 5.2742. Min Act: -0.1700
Data Index: 175205 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3055. Min Range: -5.3055
Max Act: 4.9617. Min Act: -0.1700
Data Index: 8348200 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3055. Min Range: -5.3055
Max Act: 4.9617. Min Act: -0.1700
Data Index: 7683195 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3055. Min Range: -5.3055
Max Act: 4.8992. Min Act: -0.1700
Data Index: 5429215 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3055. Min Range: -5.3055
Max Act: 4.8680. Min Act: -0.1700
Data Index: 3345823 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3055. Min Range: -5.3055
Max Act: 4.8680. Min Act: -0.1700
Data Index: 8801491 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3055. Min Range: -5.3055
Max Act: 4.8680. Min Act: -0.1700
Data Index: 3974808 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3055. Min Range: -5.3055
Max Act: 4.8680. Min Act: -0.1700
Data Index: 4597835 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3055. Min Range: -5.3055
Max Act: 4.8680. Min Act: -0.1700
Data Index: 8485341 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3055. Min Range: -5.3055
Max Act: 4.8367. Min Act: -0.1700
Data Index: 3447434 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3055. Min Range: -5.3055
Max Act: 4.8055. Min Act: -0.1700
Data Index: 5355787 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3055. Min Range: -5.3055
Max Act: 4.8055. Min Act: -0.1700
Data Index: 5248141 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3055. Min Range: -5.3055
Max Act: 4.8055. Min Act: -0.1700
Data Index: 613627 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3055. Min Range: -5.3055
Max Act: 4.8055. Min Act: -0.1700
Data Index: 8603146 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3055. Min Range: -5.3055
Max Act: 4.7742. Min Act: -0.1700
Data Index: 8030736 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3055. Min Range: -5.3055
Max Act: 4.7742. Min Act: -0.1700
Data Index: 3188165 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3055. Min Range: -5.3055
Max Act: 4.8055. Min Act: -0.1700
Data Index: 1107435 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3055. Min Range: -5.3055
Max Act: 4.7742. Min Act: -0.1700
Data Index: 133123 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3055. Min Range: -5.3055
Max Act: 4.7742. Min Act: -0.1700
Data Index: 6493809 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19