Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5535 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6180. Min Range: -6.6180
Max Act: 6.6180. Min Act: -0.1700
Data Index: 8621242 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6180. Min Range: -6.6180
Max Act: 6.5867. Min Act: -0.1700
Data Index: 4448301 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6180. Min Range: -6.6180
Max Act: 6.3680. Min Act: -0.1700
Data Index: 1778618 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6180. Min Range: -6.6180
Max Act: 6.3367. Min Act: -0.1700
Data Index: 2297903 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6180. Min Range: -6.6180
Max Act: 6.3055. Min Act: -0.1700
Data Index: 7531766 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6180. Min Range: -6.6180
Max Act: 6.3055. Min Act: -0.1700
Data Index: 5237459 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6180. Min Range: -6.6180
Max Act: 6.2742. Min Act: -0.1700
Data Index: 4685436 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6180. Min Range: -6.6180
Max Act: 6.2430. Min Act: -0.1700
Data Index: 8415219 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6180. Min Range: -6.6180
Max Act: 6.2430. Min Act: -0.1700
Data Index: 702433 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6180. Min Range: -6.6180
Max Act: 6.2430. Min Act: -0.1700
Data Index: 4654989 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6180. Min Range: -6.6180
Max Act: 6.2117. Min Act: -0.1700
Data Index: 4435009 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6180. Min Range: -6.6180
Max Act: 6.2117. Min Act: -0.1700
Data Index: 812279 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6180. Min Range: -6.6180
Max Act: 6.1805. Min Act: -0.1700
Data Index: 7625077 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6180. Min Range: -6.6180
Max Act: 6.1180. Min Act: -0.1700
Data Index: 5640288 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6180. Min Range: -6.6180
Max Act: 6.1492. Min Act: -0.1700
Data Index: 2111285 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6180. Min Range: -6.6180
Max Act: 6.1180. Min Act: -0.1700
Data Index: 8649838 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6180. Min Range: -6.6180
Max Act: 6.1492. Min Act: -0.1700
Data Index: 942631 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6180. Min Range: -6.6180
Max Act: 6.1492. Min Act: -0.1700
Data Index: 1612355 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6180. Min Range: -6.6180
Max Act: 6.1180. Min Act: -0.1700
Data Index: 3091491 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6180. Min Range: -6.6180
Max Act: 6.1180. Min Act: -0.1700
Data Index: 5802969 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #19