Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3926 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0667. Min Range: -2.0667
Max Act: 2.0667. Min Act: -0.1700
Data Index: 8111498 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0667. Min Range: -2.0667
Max Act: 2.0667. Min Act: -0.1700
Data Index: 6357876 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0667. Min Range: -2.0667
Max Act: 1.9824. Min Act: -0.1700
Data Index: 6357875 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0667. Min Range: -2.0667
Max Act: 1.9485. Min Act: -0.1700
Data Index: 4768526 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0667. Min Range: -2.0667
Max Act: 1.9145. Min Act: -0.1700
Data Index: 4296147 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0667. Min Range: -2.0667
Max Act: 1.8975. Min Act: -0.1700
Data Index: 2481672 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0667. Min Range: -2.0667
Max Act: 1.8975. Min Act: -0.1700
Data Index: 8140156 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0667. Min Range: -2.0667
Max Act: 1.8889. Min Act: -0.1700
Data Index: 5219687 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0667. Min Range: -2.0667
Max Act: 1.8718. Min Act: -0.1700
Data Index: 8655815 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0667. Min Range: -2.0667
Max Act: 1.8718. Min Act: -0.1700
Data Index: 2134512 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0667. Min Range: -2.0667
Max Act: 1.8718. Min Act: -0.1700
Data Index: 8617206 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0667. Min Range: -2.0667
Max Act: 1.8547. Min Act: -0.1699
Data Index: 905452 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0667. Min Range: -2.0667
Max Act: 1.8462. Min Act: -0.1700
Data Index: 437974 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0667. Min Range: -2.0667
Max Act: 1.8462. Min Act: -0.1700
Data Index: 4490563 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0667. Min Range: -2.0667
Max Act: 1.8462. Min Act: -0.1700
Data Index: 1091774 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0667. Min Range: -2.0667
Max Act: 1.8376. Min Act: -0.1700
Data Index: 8434223 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0667. Min Range: -2.0667
Max Act: 1.8376. Min Act: -0.1700
Data Index: 4908191 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0667. Min Range: -2.0667
Max Act: 1.8376. Min Act: -0.1700
Data Index: 5087472 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0667. Min Range: -2.0667
Max Act: 1.8376. Min Act: -0.1700
Data Index: 5625957 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0667. Min Range: -2.0667
Max Act: 1.8204. Min Act: -0.1699
Data Index: 1768123 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19