Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 766 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.8901. Min Act: -0.1700
Data Index: 5820908 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.7651. Min Act: -0.1700
Data Index: 2827685 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.6089. Min Act: -0.1700
Data Index: 33678 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.6401. Min Act: -0.1700
Data Index: 8460399 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.6401. Min Act: -0.1700
Data Index: 1314842 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.6401. Min Act: -0.1700
Data Index: 8416405 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.6401. Min Act: -0.1700
Data Index: 8324180 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.6089. Min Act: -0.1700
Data Index: 7082528 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.6089. Min Act: -0.1700
Data Index: 7167310 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.6089. Min Act: -0.1700
Data Index: 7673001 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.6401. Min Act: -0.1700
Data Index: 358571 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.5776. Min Act: -0.1700
Data Index: 4598903 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.5776. Min Act: -0.1700
Data Index: 805321 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.5464. Min Act: -0.1700
Data Index: 7399378 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.5151. Min Act: -0.1700
Data Index: 5806703 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.5464. Min Act: -0.1700
Data Index: 7957378 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.5151. Min Act: -0.1700
Data Index: 133577 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.5464. Min Act: -0.1700
Data Index: 7023180 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.5464. Min Act: -0.1700
Data Index: 826069 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.5151. Min Act: -0.1700
Data Index: 5950492 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19