Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3382 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.5857. Min Act: -0.1700
Data Index: 8107152 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.4607. Min Act: -0.1700
Data Index: 7462852 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.3357. Min Act: -0.1700
Data Index: 2533577 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.2420. Min Act: -0.1700
Data Index: 7620117 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.1795. Min Act: -0.1700
Data Index: 8652214 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.1482. Min Act: -0.1700
Data Index: 719631 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.1170. Min Act: -0.1700
Data Index: 217673 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.0857. Min Act: -0.1700
Data Index: 7381872 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.0545. Min Act: -0.1699
Data Index: 7790472 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.0545. Min Act: -0.1700
Data Index: 2008036 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.0232. Min Act: -0.1700
Data Index: 7194686 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.0545. Min Act: -0.1700
Data Index: 1005534 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5857. Min Range: -6.5857
Max Act: 5.9920. Min Act: -0.1700
Data Index: 1621113 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5857. Min Range: -6.5857
Max Act: 5.9607. Min Act: -0.1700
Data Index: 1903648 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5857. Min Range: -6.5857
Max Act: 5.9295. Min Act: -0.1700
Data Index: 3533161 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5857. Min Range: -6.5857
Max Act: 5.9295. Min Act: -0.1700
Data Index: 7371326 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5857. Min Range: -6.5857
Max Act: 5.8982. Min Act: -0.1700
Data Index: 4667796 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5857. Min Range: -6.5857
Max Act: 5.8982. Min Act: -0.1700
Data Index: 7715340 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5857. Min Range: -6.5857
Max Act: 5.9295. Min Act: -0.1700
Data Index: 6132856 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5857. Min Range: -6.5857
Max Act: 5.8670. Min Act: -0.1700
Data Index: 5851402 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19