Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3053 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0144. Min Range: -4.0144
Max Act: 4.0144. Min Act: -0.1700
Data Index: 4005218 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0144. Min Range: -4.0144
Max Act: 3.8894. Min Act: -0.1700
Data Index: 3889409 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0144. Min Range: -4.0144
Max Act: 3.8268. Min Act: -0.1700
Data Index: 6292978 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0144. Min Range: -4.0144
Max Act: 3.8581. Min Act: -0.1700
Data Index: 8694807 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0144. Min Range: -4.0144
Max Act: 3.8425. Min Act: -0.1700
Data Index: 8629340 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0144. Min Range: -4.0144
Max Act: 3.8268. Min Act: -0.1700
Data Index: 2613330 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0144. Min Range: -4.0144
Max Act: 3.7955. Min Act: -0.1700
Data Index: 145537 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0144. Min Range: -4.0144
Max Act: 3.7643. Min Act: -0.1700
Data Index: 826887 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0144. Min Range: -4.0144
Max Act: 3.7643. Min Act: -0.1700
Data Index: 6817901 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0144. Min Range: -4.0144
Max Act: 3.7330. Min Act: -0.1700
Data Index: 5313092 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0144. Min Range: -4.0144
Max Act: 3.7173. Min Act: -0.1700
Data Index: 8363762 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0144. Min Range: -4.0144
Max Act: 3.7330. Min Act: -0.1700
Data Index: 1206643 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0144. Min Range: -4.0144
Max Act: 3.7173. Min Act: -0.1700
Data Index: 2672106 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0144. Min Range: -4.0144
Max Act: 3.7017. Min Act: -0.1700
Data Index: 4918286 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0144. Min Range: -4.0144
Max Act: 3.6704. Min Act: -0.1700
Data Index: 6060820 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0144. Min Range: -4.0144
Max Act: 3.6704. Min Act: -0.1700
Data Index: 2202570 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0144. Min Range: -4.0144
Max Act: 3.6548. Min Act: -0.1700
Data Index: 766245 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0144. Min Range: -4.0144
Max Act: 3.6548. Min Act: -0.1700
Data Index: 6065883 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0144. Min Range: -4.0144
Max Act: 3.6391. Min Act: -0.1700
Data Index: 3972508 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0144. Min Range: -4.0144
Max Act: 3.6391. Min Act: -0.1700
Data Index: 2251869 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19