Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4810 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0704. Min Range: -8.0704
Max Act: 8.0704. Min Act: -0.1700
Data Index: 941981 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0704. Min Range: -8.0704
Max Act: 8.0079. Min Act: -0.1700
Data Index: 1001139 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0704. Min Range: -8.0704
Max Act: 7.8204. Min Act: -0.1700
Data Index: 1493711 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0704. Min Range: -8.0704
Max Act: 7.7579. Min Act: -0.1700
Data Index: 3011143 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0704. Min Range: -8.0704
Max Act: 7.7579. Min Act: -0.1700
Data Index: 5019031 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0704. Min Range: -8.0704
Max Act: 7.8204. Min Act: -0.1700
Data Index: 3103144 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0704. Min Range: -8.0704
Max Act: 7.6954. Min Act: -0.1700
Data Index: 4750970 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0704. Min Range: -8.0704
Max Act: 7.6954. Min Act: -0.1700
Data Index: 2018180 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0704. Min Range: -8.0704
Max Act: 7.6954. Min Act: -0.1700
Data Index: 3298494 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0704. Min Range: -8.0704
Max Act: 7.6954. Min Act: -0.1700
Data Index: 1654869 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0704. Min Range: -8.0704
Max Act: 7.7579. Min Act: -0.1700
Data Index: 3816432 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0704. Min Range: -8.0704
Max Act: 7.6954. Min Act: -0.1700
Data Index: 7012495 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0704. Min Range: -8.0704
Max Act: 7.6329. Min Act: -0.1700
Data Index: 4290659 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0704. Min Range: -8.0704
Max Act: 7.6329. Min Act: -0.1700
Data Index: 7058211 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0704. Min Range: -8.0704
Max Act: 7.6329. Min Act: -0.1700
Data Index: 4398108 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0704. Min Range: -8.0704
Max Act: 7.5704. Min Act: -0.1700
Data Index: 2688698 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0704. Min Range: -8.0704
Max Act: 7.5704. Min Act: -0.1700
Data Index: 3537559 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0704. Min Range: -8.0704
Max Act: 7.5704. Min Act: -0.1700
Data Index: 4840644 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0704. Min Range: -8.0704
Max Act: 7.5704. Min Act: -0.1700
Data Index: 1815535 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0704. Min Range: -8.0704
Max Act: 7.5704. Min Act: -0.1700
Data Index: 1210888 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19