Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3319 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5789. Min Range: -4.5789
Max Act: 4.5789. Min Act: -0.1700
Data Index: 3511206 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5789. Min Range: -4.5789
Max Act: 4.5476. Min Act: -0.1700
Data Index: 4322770 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5789. Min Range: -4.5789
Max Act: 4.4539. Min Act: -0.1700
Data Index: 5272003 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5789. Min Range: -4.5789
Max Act: 4.4539. Min Act: -0.1700
Data Index: 6625607 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5789. Min Range: -4.5789
Max Act: 4.4539. Min Act: -0.1700
Data Index: 3868335 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5789. Min Range: -4.5789
Max Act: 4.4851. Min Act: -0.1700
Data Index: 256712 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5789. Min Range: -4.5789
Max Act: 4.3914. Min Act: -0.1700
Data Index: 2619886 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5789. Min Range: -4.5789
Max Act: 4.3914. Min Act: -0.1700
Data Index: 5064742 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5789. Min Range: -4.5789
Max Act: 4.3914. Min Act: -0.1700
Data Index: 1028494 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5789. Min Range: -4.5789
Max Act: 4.3914. Min Act: -0.1700
Data Index: 5399825 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5789. Min Range: -4.5789
Max Act: 4.3914. Min Act: -0.1700
Data Index: 3326885 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5789. Min Range: -4.5789
Max Act: 4.3914. Min Act: -0.1700
Data Index: 4440474 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5789. Min Range: -4.5789
Max Act: 4.3914. Min Act: -0.1700
Data Index: 2781016 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5789. Min Range: -4.5789
Max Act: 4.3601. Min Act: -0.1700
Data Index: 8538481 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5789. Min Range: -4.5789
Max Act: 4.3601. Min Act: -0.1700
Data Index: 652010 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5789. Min Range: -4.5789
Max Act: 4.3601. Min Act: -0.1700
Data Index: 539523 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5789. Min Range: -4.5789
Max Act: 4.3601. Min Act: -0.1700
Data Index: 6644173 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5789. Min Range: -4.5789
Max Act: 4.3601. Min Act: -0.1700
Data Index: 3276371 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5789. Min Range: -4.5789
Max Act: 4.3601. Min Act: -0.1700
Data Index: 123142 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5789. Min Range: -4.5789
Max Act: 4.3288. Min Act: -0.1700
Data Index: 384806 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #19