Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4563 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6156. Min Range: -6.6156
Max Act: 6.6156. Min Act: -0.1700
Data Index: 1810629 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6156. Min Range: -6.6156
Max Act: 6.5219. Min Act: -0.1700
Data Index: 4958592 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6156. Min Range: -6.6156
Max Act: 6.4906. Min Act: -0.1700
Data Index: 3981074 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6156. Min Range: -6.6156
Max Act: 6.4906. Min Act: -0.1700
Data Index: 6877611 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6156. Min Range: -6.6156
Max Act: 6.3656. Min Act: -0.1700
Data Index: 8214647 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6156. Min Range: -6.6156
Max Act: 6.3344. Min Act: -0.1700
Data Index: 3676175 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6156. Min Range: -6.6156
Max Act: 6.3344. Min Act: -0.1700
Data Index: 779173 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6156. Min Range: -6.6156
Max Act: 6.3031. Min Act: -0.1700
Data Index: 2677631 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6156. Min Range: -6.6156
Max Act: 6.3031. Min Act: -0.1700
Data Index: 7250855 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6156. Min Range: -6.6156
Max Act: 6.3031. Min Act: -0.1700
Data Index: 1683558 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6156. Min Range: -6.6156
Max Act: 6.3031. Min Act: -0.1700
Data Index: 2347345 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6156. Min Range: -6.6156
Max Act: 6.3031. Min Act: -0.1700
Data Index: 7464850 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6156. Min Range: -6.6156
Max Act: 6.2719. Min Act: -0.1700
Data Index: 8286517 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6156. Min Range: -6.6156
Max Act: 6.2719. Min Act: -0.1700
Data Index: 5060048 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6156. Min Range: -6.6156
Max Act: 6.2719. Min Act: -0.1700
Data Index: 5598306 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6156. Min Range: -6.6156
Max Act: 6.2406. Min Act: -0.1700
Data Index: 5748948 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6156. Min Range: -6.6156
Max Act: 6.2719. Min Act: -0.1700
Data Index: 8522086 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6156. Min Range: -6.6156
Max Act: 6.2406. Min Act: -0.1700
Data Index: 8768240 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6156. Min Range: -6.6156
Max Act: 6.2406. Min Act: -0.1700
Data Index: 380749 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6156. Min Range: -6.6156
Max Act: 6.2094. Min Act: -0.1700
Data Index: 3691765 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19