Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2850 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7072. Min Range: -6.7072
Max Act: 6.7072. Min Act: -0.1700
Data Index: 1101536 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7072. Min Range: -6.7072
Max Act: 6.5197. Min Act: -0.1700
Data Index: 7530600 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7072. Min Range: -6.7072
Max Act: 6.4260. Min Act: -0.1700
Data Index: 1937724 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7072. Min Range: -6.7072
Max Act: 6.3635. Min Act: -0.1700
Data Index: 8432447 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7072. Min Range: -6.7072
Max Act: 6.3635. Min Act: -0.1700
Data Index: 6319904 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7072. Min Range: -6.7072
Max Act: 6.3635. Min Act: -0.1700
Data Index: 5554906 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7072. Min Range: -6.7072
Max Act: 6.3635. Min Act: -0.1700
Data Index: 3389990 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7072. Min Range: -6.7072
Max Act: 6.3635. Min Act: -0.1700
Data Index: 8305757 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7072. Min Range: -6.7072
Max Act: 6.3322. Min Act: -0.1700
Data Index: 433813 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7072. Min Range: -6.7072
Max Act: 6.2072. Min Act: -0.1700
Data Index: 5570203 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7072. Min Range: -6.7072
Max Act: 6.2072. Min Act: -0.1700
Data Index: 5423686 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7072. Min Range: -6.7072
Max Act: 6.1447. Min Act: -0.1700
Data Index: 2538563 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7072. Min Range: -6.7072
Max Act: 6.1135. Min Act: -0.1700
Data Index: 6159014 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7072. Min Range: -6.7072
Max Act: 6.1135. Min Act: -0.1700
Data Index: 987283 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7072. Min Range: -6.7072
Max Act: 6.1135. Min Act: -0.1700
Data Index: 2229182 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7072. Min Range: -6.7072
Max Act: 6.1447. Min Act: -0.1700
Data Index: 5586006 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7072. Min Range: -6.7072
Max Act: 6.1135. Min Act: -0.1700
Data Index: 5221011 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7072. Min Range: -6.7072
Max Act: 6.0822. Min Act: -0.1700
Data Index: 6035566 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7072. Min Range: -6.7072
Max Act: 6.0510. Min Act: -0.1700
Data Index: 3729569 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7072. Min Range: -6.7072
Max Act: 6.0197. Min Act: -0.1700
Data Index: 7844274 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19