Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3346 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9998. Min Range: -3.9998
Max Act: 3.9998. Min Act: -0.1700
Data Index: 1950227 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9998. Min Range: -3.9998
Max Act: 3.9685. Min Act: -0.1700
Data Index: 7431924 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9998. Min Range: -3.9998
Max Act: 3.9373. Min Act: -0.1700
Data Index: 5784594 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9998. Min Range: -3.9998
Max Act: 3.8747. Min Act: -0.1700
Data Index: 8608546 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9998. Min Range: -3.9998
Max Act: 3.8435. Min Act: -0.1700
Data Index: 4502883 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9998. Min Range: -3.9998
Max Act: 3.8122. Min Act: -0.1700
Data Index: 1854898 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9998. Min Range: -3.9998
Max Act: 3.8122. Min Act: -0.1700
Data Index: 5511554 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9998. Min Range: -3.9998
Max Act: 3.7809. Min Act: -0.1700
Data Index: 1191929 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9998. Min Range: -3.9998
Max Act: 3.7809. Min Act: -0.1700
Data Index: 5960896 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9998. Min Range: -3.9998
Max Act: 3.7809. Min Act: -0.1700
Data Index: 5653888 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9998. Min Range: -3.9998
Max Act: 3.7496. Min Act: -0.1700
Data Index: 3904610 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9998. Min Range: -3.9998
Max Act: 3.7496. Min Act: -0.1700
Data Index: 8658774 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9998. Min Range: -3.9998
Max Act: 3.7809. Min Act: -0.1700
Data Index: 1839386 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9998. Min Range: -3.9998
Max Act: 3.7496. Min Act: -0.1700
Data Index: 1302204 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9998. Min Range: -3.9998
Max Act: 3.7496. Min Act: -0.1700
Data Index: 2073169 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9998. Min Range: -3.9998
Max Act: 3.7496. Min Act: -0.1700
Data Index: 8389604 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9998. Min Range: -3.9998
Max Act: 3.7496. Min Act: -0.1700
Data Index: 5702341 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9998. Min Range: -3.9998
Max Act: 3.7496. Min Act: -0.1700
Data Index: 1300613 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9998. Min Range: -3.9998
Max Act: 3.7184. Min Act: -0.1700
Data Index: 5702342 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9998. Min Range: -3.9998
Max Act: 3.7340. Min Act: -0.1700
Data Index: 4960658 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19