Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3166 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6359. Min Range: -7.6359
Max Act: 7.6359. Min Act: -0.1700
Data Index: 8562649 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6359. Min Range: -7.6359
Max Act: 7.4172. Min Act: -0.1700
Data Index: 5445531 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6359. Min Range: -7.6359
Max Act: 7.1672. Min Act: -0.1700
Data Index: 2063233 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6359. Min Range: -7.6359
Max Act: 7.0734. Min Act: -0.1700
Data Index: 584568 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6359. Min Range: -7.6359
Max Act: 7.0109. Min Act: -0.1700
Data Index: 2996217 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6359. Min Range: -7.6359
Max Act: 6.9172. Min Act: -0.1700
Data Index: 3191254 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6359. Min Range: -7.6359
Max Act: 6.9172. Min Act: -0.1700
Data Index: 5455858 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6359. Min Range: -7.6359
Max Act: 6.9172. Min Act: -0.1700
Data Index: 4229542 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6359. Min Range: -7.6359
Max Act: 6.9172. Min Act: -0.1700
Data Index: 4632154 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6359. Min Range: -7.6359
Max Act: 6.8859. Min Act: -0.1700
Data Index: 2334492 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6359. Min Range: -7.6359
Max Act: 6.8859. Min Act: -0.1700
Data Index: 1908345 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6359. Min Range: -7.6359
Max Act: 6.8859. Min Act: -0.1700
Data Index: 60156 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6359. Min Range: -7.6359
Max Act: 6.8859. Min Act: -0.1700
Data Index: 2510313 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6359. Min Range: -7.6359
Max Act: 6.8547. Min Act: -0.1700
Data Index: 867492 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6359. Min Range: -7.6359
Max Act: 6.8547. Min Act: -0.1700
Data Index: 979529 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6359. Min Range: -7.6359
Max Act: 6.8547. Min Act: -0.1700
Data Index: 942620 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6359. Min Range: -7.6359
Max Act: 6.8234. Min Act: -0.1700
Data Index: 4104267 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6359. Min Range: -7.6359
Max Act: 6.8234. Min Act: -0.1700
Data Index: 7380106 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6359. Min Range: -7.6359
Max Act: 6.7922. Min Act: -0.1700
Data Index: 5172550 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6359. Min Range: -7.6359
Max Act: 6.7609. Min Act: -0.1700
Data Index: 1072895 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #19