Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 404 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2593. Min Range: -8.2593
Max Act: 8.2593. Min Act: -0.1700
Data Index: 3727987 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2593. Min Range: -8.2593
Max Act: 7.8218. Min Act: -0.1700
Data Index: 6489591 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2593. Min Range: -8.2593
Max Act: 7.7593. Min Act: -0.1700
Data Index: 1870889 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2593. Min Range: -8.2593
Max Act: 7.6968. Min Act: -0.1700
Data Index: 2810675 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2593. Min Range: -8.2593
Max Act: 7.7281. Min Act: -0.1700
Data Index: 5248007 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2593. Min Range: -8.2593
Max Act: 7.7593. Min Act: -0.1700
Data Index: 8186078 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2593. Min Range: -8.2593
Max Act: 7.6031. Min Act: -0.1700
Data Index: 1641618 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2593. Min Range: -8.2593
Max Act: 7.5093. Min Act: -0.1700
Data Index: 7410914 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2593. Min Range: -8.2593
Max Act: 7.5093. Min Act: -0.1700
Data Index: 1793102 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2593. Min Range: -8.2593
Max Act: 7.5093. Min Act: -0.1700
Data Index: 1443677 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2593. Min Range: -8.2593
Max Act: 7.5093. Min Act: -0.1700
Data Index: 3066383 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2593. Min Range: -8.2593
Max Act: 7.4468. Min Act: -0.1700
Data Index: 4096872 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2593. Min Range: -8.2593
Max Act: 7.4156. Min Act: -0.1700
Data Index: 7222743 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2593. Min Range: -8.2593
Max Act: 7.4781. Min Act: -0.1700
Data Index: 952015 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2593. Min Range: -8.2593
Max Act: 7.4781. Min Act: -0.1700
Data Index: 8544734 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2593. Min Range: -8.2593
Max Act: 7.4156. Min Act: -0.1700
Data Index: 8518549 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2593. Min Range: -8.2593
Max Act: 7.4156. Min Act: -0.1700
Data Index: 1521425 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2593. Min Range: -8.2593
Max Act: 7.4156. Min Act: -0.1700
Data Index: 7586722 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2593. Min Range: -8.2593
Max Act: 7.4156. Min Act: -0.1700
Data Index: 726753 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2593. Min Range: -8.2593
Max Act: 7.4156. Min Act: -0.1700
Data Index: 614235 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #19