Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5016 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3200. Min Range: -5.3200
Max Act: 5.3200. Min Act: -0.1700
Data Index: 1297575 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3200. Min Range: -5.3200
Max Act: 5.2887. Min Act: -0.1700
Data Index: 4032215 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3200. Min Range: -5.3200
Max Act: 5.2575. Min Act: -0.1700
Data Index: 4333462 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3200. Min Range: -5.3200
Max Act: 5.2262. Min Act: -0.1700
Data Index: 8364276 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3200. Min Range: -5.3200
Max Act: 5.1637. Min Act: -0.1700
Data Index: 6480177 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3200. Min Range: -5.3200
Max Act: 5.1012. Min Act: -0.1700
Data Index: 3771932 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3200. Min Range: -5.3200
Max Act: 5.1012. Min Act: -0.1700
Data Index: 1922034 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3200. Min Range: -5.3200
Max Act: 5.1012. Min Act: -0.1700
Data Index: 3219496 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3200. Min Range: -5.3200
Max Act: 5.0387. Min Act: -0.1700
Data Index: 1962126 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3200. Min Range: -5.3200
Max Act: 5.0387. Min Act: -0.1700
Data Index: 5932479 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3200. Min Range: -5.3200
Max Act: 5.0387. Min Act: -0.1700
Data Index: 4228185 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3200. Min Range: -5.3200
Max Act: 5.0075. Min Act: -0.1700
Data Index: 7530455 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3200. Min Range: -5.3200
Max Act: 5.0075. Min Act: -0.1700
Data Index: 2258505 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3200. Min Range: -5.3200
Max Act: 4.9762. Min Act: -0.1700
Data Index: 7590432 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3200. Min Range: -5.3200
Max Act: 4.9762. Min Act: -0.1700
Data Index: 3929212 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3200. Min Range: -5.3200
Max Act: 4.9762. Min Act: -0.1700
Data Index: 4460715 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3200. Min Range: -5.3200
Max Act: 4.9762. Min Act: -0.1700
Data Index: 351406 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3200. Min Range: -5.3200
Max Act: 4.9450. Min Act: -0.1700
Data Index: 1125126 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3200. Min Range: -5.3200
Max Act: 4.9450. Min Act: -0.1700
Data Index: 2951644 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3200. Min Range: -5.3200
Max Act: 4.9450. Min Act: -0.1700
Data Index: 583982 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19