Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 18 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4591. Min Range: -7.4591
Max Act: 7.4591. Min Act: -0.1700
Data Index: 7262892 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4591. Min Range: -7.4591
Max Act: 7.2404. Min Act: -0.1700
Data Index: 5073543 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4591. Min Range: -7.4591
Max Act: 7.2404. Min Act: -0.1700
Data Index: 1834562 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4591. Min Range: -7.4591
Max Act: 7.2404. Min Act: -0.1700
Data Index: 8422400 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4591. Min Range: -7.4591
Max Act: 7.1779. Min Act: -0.1700
Data Index: 5581905 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4591. Min Range: -7.4591
Max Act: 7.1779. Min Act: -0.1700
Data Index: 2236670 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4591. Min Range: -7.4591
Max Act: 7.1779. Min Act: -0.1700
Data Index: 8077076 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4591. Min Range: -7.4591
Max Act: 7.1466. Min Act: -0.1700
Data Index: 1834563 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4591. Min Range: -7.4591
Max Act: 7.1466. Min Act: -0.1700
Data Index: 619541 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4591. Min Range: -7.4591
Max Act: 7.1466. Min Act: -0.1700
Data Index: 8094498 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4591. Min Range: -7.4591
Max Act: 7.1154. Min Act: -0.1700
Data Index: 5581906 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4591. Min Range: -7.4591
Max Act: 7.0529. Min Act: -0.1700
Data Index: 7403012 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4591. Min Range: -7.4591
Max Act: 7.0529. Min Act: -0.1700
Data Index: 5581907 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4591. Min Range: -7.4591
Max Act: 7.0216. Min Act: -0.1700
Data Index: 3984621 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4591. Min Range: -7.4591
Max Act: 6.9904. Min Act: -0.1700
Data Index: 8305821 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4591. Min Range: -7.4591
Max Act: 6.9904. Min Act: -0.1700
Data Index: 7348852 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4591. Min Range: -7.4591
Max Act: 6.9904. Min Act: -0.1700
Data Index: 8322841 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4591. Min Range: -7.4591
Max Act: 6.9591. Min Act: -0.1700
Data Index: 1694070 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4591. Min Range: -7.4591
Max Act: 6.9591. Min Act: -0.1700
Data Index: 2121577 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4591. Min Range: -7.4591
Max Act: 6.9591. Min Act: -0.1700
Data Index: 1418803 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19