Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2647 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6589. Min Range: -6.6589
Max Act: 6.6589. Min Act: -0.1700
Data Index: 5960098 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6589. Min Range: -6.6589
Max Act: 6.4402. Min Act: -0.1700
Data Index: 2488685 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6589. Min Range: -6.6589
Max Act: 6.3777. Min Act: -0.1700
Data Index: 7929809 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6589. Min Range: -6.6589
Max Act: 6.3152. Min Act: -0.1700
Data Index: 8683134 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6589. Min Range: -6.6589
Max Act: 6.3464. Min Act: -0.1700
Data Index: 2510695 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6589. Min Range: -6.6589
Max Act: 6.2839. Min Act: -0.1700
Data Index: 8188419 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6589. Min Range: -6.6589
Max Act: 6.2839. Min Act: -0.1700
Data Index: 1809323 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6589. Min Range: -6.6589
Max Act: 6.1902. Min Act: -0.1700
Data Index: 4035814 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6589. Min Range: -6.6589
Max Act: 6.1589. Min Act: -0.1700
Data Index: 7780809 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6589. Min Range: -6.6589
Max Act: 6.1277. Min Act: -0.1700
Data Index: 5246695 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6589. Min Range: -6.6589
Max Act: 6.0964. Min Act: -0.1700
Data Index: 3343835 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6589. Min Range: -6.6589
Max Act: 6.0964. Min Act: -0.1700
Data Index: 3794501 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6589. Min Range: -6.6589
Max Act: 6.0652. Min Act: -0.1700
Data Index: 2939360 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6589. Min Range: -6.6589
Max Act: 6.0652. Min Act: -0.1700
Data Index: 6129808 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6589. Min Range: -6.6589
Max Act: 6.0339. Min Act: -0.1700
Data Index: 4789280 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6589. Min Range: -6.6589
Max Act: 6.0339. Min Act: -0.1700
Data Index: 3944977 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6589. Min Range: -6.6589
Max Act: 6.0027. Min Act: -0.1700
Data Index: 5306780 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6589. Min Range: -6.6589
Max Act: 6.0027. Min Act: -0.1700
Data Index: 7955147 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6589. Min Range: -6.6589
Max Act: 6.0027. Min Act: -0.1700
Data Index: 195122 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6589. Min Range: -6.6589
Max Act: 6.0027. Min Act: -0.1700
Data Index: 3356221 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #19