Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 684 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5198. Min Range: -9.5198
Max Act: 9.5198. Min Act: -0.1700
Data Index: 4534292 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5198. Min Range: -9.5198
Max Act: 9.3948. Min Act: -0.1700
Data Index: 7431931 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5198. Min Range: -9.5198
Max Act: 9.3948. Min Act: -0.1700
Data Index: 324734 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5198. Min Range: -9.5198
Max Act: 9.3323. Min Act: -0.1700
Data Index: 7643470 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5198. Min Range: -9.5198
Max Act: 9.3323. Min Act: -0.1700
Data Index: 8528869 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5198. Min Range: -9.5198
Max Act: 9.3323. Min Act: -0.1700
Data Index: 7731817 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5198. Min Range: -9.5198
Max Act: 9.2698. Min Act: -0.1700
Data Index: 38329 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5198. Min Range: -9.5198
Max Act: 9.2698. Min Act: -0.1700
Data Index: 227413 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5198. Min Range: -9.5198
Max Act: 9.2698. Min Act: -0.1700
Data Index: 3714997 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5198. Min Range: -9.5198
Max Act: 9.2073. Min Act: -0.1700
Data Index: 1145827 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5198. Min Range: -9.5198
Max Act: 9.2073. Min Act: -0.1700
Data Index: 1152208 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5198. Min Range: -9.5198
Max Act: 9.2073. Min Act: -0.1700
Data Index: 4683184 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5198. Min Range: -9.5198
Max Act: 9.2073. Min Act: -0.1700
Data Index: 2053477 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5198. Min Range: -9.5198
Max Act: 9.1448. Min Act: -0.1700
Data Index: 4723494 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5198. Min Range: -9.5198
Max Act: 9.1448. Min Act: -0.1700
Data Index: 5958096 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5198. Min Range: -9.5198
Max Act: 9.1448. Min Act: -0.1700
Data Index: 5809289 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5198. Min Range: -9.5198
Max Act: 9.0823. Min Act: -0.1700
Data Index: 2037872 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5198. Min Range: -9.5198
Max Act: 9.0823. Min Act: -0.1700
Data Index: 6677752 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5198. Min Range: -9.5198
Max Act: 9.0823. Min Act: -0.1700
Data Index: 3075497 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5198. Min Range: -9.5198
Max Act: 9.0198. Min Act: -0.1700
Data Index: 4401702 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19