Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2274 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3607. Min Range: -10.3607
Max Act: 10.3607. Min Act: -0.1697
Data Index: 2553388 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3607. Min Range: -10.3607
Max Act: 9.8607. Min Act: -0.1700
Data Index: 8831973 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3607. Min Range: -10.3607
Max Act: 9.4232. Min Act: -0.1700
Data Index: 3664144 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3607. Min Range: -10.3607
Max Act: 9.2357. Min Act: -0.1700
Data Index: 2850335 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3607. Min Range: -10.3607
Max Act: 9.1107. Min Act: -0.1700
Data Index: 7156940 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3607. Min Range: -10.3607
Max Act: 9.0482. Min Act: -0.1700
Data Index: 5730144 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3607. Min Range: -10.3607
Max Act: 8.9232. Min Act: -0.1700
Data Index: 1945153 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3607. Min Range: -10.3607
Max Act: 8.9232. Min Act: -0.1700
Data Index: 4390515 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3607. Min Range: -10.3607
Max Act: 8.9232. Min Act: -0.1700
Data Index: 1888914 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3607. Min Range: -10.3607
Max Act: 8.9232. Min Act: -0.1700
Data Index: 6804161 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3607. Min Range: -10.3607
Max Act: 8.8607. Min Act: -0.1700
Data Index: 4681615 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3607. Min Range: -10.3607
Max Act: 8.8607. Min Act: -0.1700
Data Index: 1542221 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3607. Min Range: -10.3607
Max Act: 8.7982. Min Act: -0.1700
Data Index: 7654821 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3607. Min Range: -10.3607
Max Act: 8.7357. Min Act: -0.1687
Data Index: 6834821 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3607. Min Range: -10.3607
Max Act: 8.6732. Min Act: -0.1700
Data Index: 33534 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3607. Min Range: -10.3607
Max Act: 8.7357. Min Act: -0.1700
Data Index: 1041479 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3607. Min Range: -10.3607
Max Act: 8.7357. Min Act: -0.1700
Data Index: 7764939 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3607. Min Range: -10.3607
Max Act: 8.7357. Min Act: -0.1700
Data Index: 2777769 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3607. Min Range: -10.3607
Max Act: 8.6732. Min Act: -0.1700
Data Index: 3352879 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3607. Min Range: -10.3607
Max Act: 8.6732. Min Act: -0.1700
Data Index: 2337622 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #19