Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5110 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5503. Min Range: -6.5503
Max Act: 6.5503. Min Act: -0.1700
Data Index: 2624554 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5503. Min Range: -6.5503
Max Act: 5.8003. Min Act: -0.1700
Data Index: 6595311 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5503. Min Range: -6.5503
Max Act: 5.7691. Min Act: -0.1700
Data Index: 5077623 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5503. Min Range: -6.5503
Max Act: 5.7691. Min Act: -0.1700
Data Index: 4755597 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5503. Min Range: -6.5503
Max Act: 5.7378. Min Act: -0.1700
Data Index: 5897904 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5503. Min Range: -6.5503
Max Act: 5.6753. Min Act: -0.1700
Data Index: 607498 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5503. Min Range: -6.5503
Max Act: 5.7066. Min Act: -0.1700
Data Index: 4441426 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5503. Min Range: -6.5503
Max Act: 5.7066. Min Act: -0.1700
Data Index: 2145462 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5503. Min Range: -6.5503
Max Act: 5.6441. Min Act: -0.1700
Data Index: 7549327 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5503. Min Range: -6.5503
Max Act: 5.6441. Min Act: -0.1700
Data Index: 248425 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5503. Min Range: -6.5503
Max Act: 5.6128. Min Act: -0.1700
Data Index: 3804640 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5503. Min Range: -6.5503
Max Act: 5.6128. Min Act: -0.1700
Data Index: 7700467 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5503. Min Range: -6.5503
Max Act: 5.6128. Min Act: -0.1700
Data Index: 5468489 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5503. Min Range: -6.5503
Max Act: 5.5816. Min Act: -0.1700
Data Index: 4617592 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5503. Min Range: -6.5503
Max Act: 5.5816. Min Act: -0.1700
Data Index: 1841710 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5503. Min Range: -6.5503
Max Act: 5.5503. Min Act: -0.1700
Data Index: 4341835 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5503. Min Range: -6.5503
Max Act: 5.5503. Min Act: -0.1700
Data Index: 2296232 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5503. Min Range: -6.5503
Max Act: 5.5191. Min Act: -0.1700
Data Index: 1058780 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5503. Min Range: -6.5503
Max Act: 5.5191. Min Act: -0.1700
Data Index: 6833990 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5503. Min Range: -6.5503
Max Act: 5.5191. Min Act: -0.1700
Data Index: 5453648 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19