Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1669 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6061. Min Range: -5.6061
Max Act: 5.6061. Min Act: -0.1700
Data Index: 733171 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6061. Min Range: -5.6061
Max Act: 5.5436. Min Act: -0.1700
Data Index: 8777504 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6061. Min Range: -5.6061
Max Act: 5.4499. Min Act: -0.1700
Data Index: 1857266 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6061. Min Range: -5.6061
Max Act: 5.4499. Min Act: -0.1700
Data Index: 5491817 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6061. Min Range: -5.6061
Max Act: 5.3874. Min Act: -0.1700
Data Index: 7854545 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6061. Min Range: -5.6061
Max Act: 5.3874. Min Act: -0.1700
Data Index: 1920720 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6061. Min Range: -5.6061
Max Act: 5.3561. Min Act: -0.1700
Data Index: 903058 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6061. Min Range: -5.6061
Max Act: 5.3874. Min Act: -0.1700
Data Index: 2704934 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6061. Min Range: -5.6061
Max Act: 5.3561. Min Act: -0.1700
Data Index: 2014581 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6061. Min Range: -5.6061
Max Act: 5.2936. Min Act: -0.1700
Data Index: 6099915 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6061. Min Range: -5.6061
Max Act: 5.2624. Min Act: -0.1700
Data Index: 1632293 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6061. Min Range: -5.6061
Max Act: 5.3249. Min Act: -0.1700
Data Index: 5675581 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6061. Min Range: -5.6061
Max Act: 5.3249. Min Act: -0.1700
Data Index: 4791613 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6061. Min Range: -5.6061
Max Act: 5.3249. Min Act: -0.1700
Data Index: 5375856 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6061. Min Range: -5.6061
Max Act: 5.3249. Min Act: -0.1700
Data Index: 5128294 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6061. Min Range: -5.6061
Max Act: 5.3249. Min Act: -0.1700
Data Index: 7109895 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6061. Min Range: -5.6061
Max Act: 5.2624. Min Act: -0.1700
Data Index: 542337 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6061. Min Range: -5.6061
Max Act: 5.3249. Min Act: -0.1700
Data Index: 7964088 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6061. Min Range: -5.6061
Max Act: 5.2624. Min Act: -0.1700
Data Index: 4779946 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6061. Min Range: -5.6061
Max Act: 5.3249. Min Act: -0.1700
Data Index: 1725884 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19