Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2644 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3830. Min Range: -8.3830
Max Act: 8.3205. Min Act: -0.1700
Data Index: 6137478 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3830. Min Range: -8.3830
Max Act: 8.3830. Min Act: -0.1700
Data Index: 8644275 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3830. Min Range: -8.3830
Max Act: 8.1330. Min Act: -0.1700
Data Index: 4973284 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3830. Min Range: -8.3830
Max Act: 8.1330. Min Act: -0.1700
Data Index: 6969742 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3830. Min Range: -8.3830
Max Act: 7.9143. Min Act: -0.1700
Data Index: 7065806 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3830. Min Range: -8.3830
Max Act: 7.9143. Min Act: -0.1700
Data Index: 6063441 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3830. Min Range: -8.3830
Max Act: 7.9143. Min Act: -0.1700
Data Index: 4496013 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3830. Min Range: -8.3830
Max Act: 7.9143. Min Act: -0.1700
Data Index: 7606884 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3830. Min Range: -8.3830
Max Act: 7.8830. Min Act: -0.1700
Data Index: 2194640 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3830. Min Range: -8.3830
Max Act: 7.7893. Min Act: -0.1700
Data Index: 5019827 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3830. Min Range: -8.3830
Max Act: 7.7893. Min Act: -0.1700
Data Index: 2809946 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3830. Min Range: -8.3830
Max Act: 7.7268. Min Act: -0.1700
Data Index: 4873181 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3830. Min Range: -8.3830
Max Act: 7.7268. Min Act: -0.1700
Data Index: 5443033 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3830. Min Range: -8.3830
Max Act: 7.7268. Min Act: -0.1700
Data Index: 3022202 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3830. Min Range: -8.3830
Max Act: 7.7268. Min Act: -0.1700
Data Index: 8378612 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3830. Min Range: -8.3830
Max Act: 7.6955. Min Act: -0.1700
Data Index: 4220658 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3830. Min Range: -8.3830
Max Act: 7.6955. Min Act: -0.1700
Data Index: 1845820 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3830. Min Range: -8.3830
Max Act: 7.6643. Min Act: -0.1700
Data Index: 5415892 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3830. Min Range: -8.3830
Max Act: 7.6643. Min Act: -0.1700
Data Index: 1604852 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3830. Min Range: -8.3830
Max Act: 7.6643. Min Act: -0.1700
Data Index: 4708019 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19