Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 310 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2001. Min Range: -6.2001
Max Act: 6.2001. Min Act: -0.1700
Data Index: 979733 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2001. Min Range: -6.2001
Max Act: 6.1688. Min Act: -0.1700
Data Index: 862175 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2001. Min Range: -6.2001
Max Act: 6.1063. Min Act: -0.1700
Data Index: 5265862 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2001. Min Range: -6.2001
Max Act: 6.0751. Min Act: -0.1700
Data Index: 2294962 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2001. Min Range: -6.2001
Max Act: 6.0751. Min Act: -0.1700
Data Index: 19539 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2001. Min Range: -6.2001
Max Act: 5.9188. Min Act: -0.1700
Data Index: 5485445 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2001. Min Range: -6.2001
Max Act: 5.9188. Min Act: -0.1700
Data Index: 3193998 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2001. Min Range: -6.2001
Max Act: 5.9188. Min Act: -0.1700
Data Index: 4416636 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2001. Min Range: -6.2001
Max Act: 5.8876. Min Act: -0.1700
Data Index: 435574 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2001. Min Range: -6.2001
Max Act: 5.8876. Min Act: -0.1700
Data Index: 466479 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2001. Min Range: -6.2001
Max Act: 5.8876. Min Act: -0.1700
Data Index: 3374094 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2001. Min Range: -6.2001
Max Act: 5.8876. Min Act: -0.1700
Data Index: 2946867 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2001. Min Range: -6.2001
Max Act: 5.9188. Min Act: -0.1700
Data Index: 2258252 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2001. Min Range: -6.2001
Max Act: 5.8563. Min Act: -0.1700
Data Index: 7464825 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2001. Min Range: -6.2001
Max Act: 5.8563. Min Act: -0.1700
Data Index: 6750387 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2001. Min Range: -6.2001
Max Act: 5.8563. Min Act: -0.1700
Data Index: 4934361 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2001. Min Range: -6.2001
Max Act: 5.7938. Min Act: -0.1700
Data Index: 7773041 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2001. Min Range: -6.2001
Max Act: 5.8251. Min Act: -0.1700
Data Index: 6481904 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2001. Min Range: -6.2001
Max Act: 5.8251. Min Act: -0.1700
Data Index: 3374668 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2001. Min Range: -6.2001
Max Act: 5.7938. Min Act: -0.1700
Data Index: 7392146 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19