Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4056 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 12.7012. Min Range: -12.7012
Max Act: 12.7012. Min Act: -0.1700
Data Index: 7720190 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.7012. Min Range: -12.7012
Max Act: 12.6387. Min Act: -0.1700
Data Index: 2282437 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.7012. Min Range: -12.7012
Max Act: 12.2012. Min Act: -0.1700
Data Index: 5718376 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.7012. Min Range: -12.7012
Max Act: 12.2637. Min Act: -0.1700
Data Index: 8796740 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.7012. Min Range: -12.7012
Max Act: 12.0762. Min Act: -0.1700
Data Index: 8583752 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.7012. Min Range: -12.7012
Max Act: 11.9512. Min Act: -0.1700
Data Index: 5651269 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.7012. Min Range: -12.7012
Max Act: 11.5762. Min Act: -0.1700
Data Index: 3183817 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.7012. Min Range: -12.7012
Max Act: 11.5137. Min Act: -0.1700
Data Index: 6856695 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.7012. Min Range: -12.7012
Max Act: 11.5137. Min Act: -0.1700
Data Index: 7547541 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.7012. Min Range: -12.7012
Max Act: 11.0762. Min Act: -0.1700
Data Index: 5299424 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.7012. Min Range: -12.7012
Max Act: 11.2012. Min Act: -0.1700
Data Index: 3027887 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.7012. Min Range: -12.7012
Max Act: 10.3887. Min Act: -0.1700
Data Index: 1567884 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.7012. Min Range: -12.7012
Max Act: 11.2012. Min Act: -0.1700
Data Index: 2920291 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.7012. Min Range: -12.7012
Max Act: 10.8887. Min Act: -0.1700
Data Index: 2126890 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.7012. Min Range: -12.7012
Max Act: 10.8887. Min Act: -0.1700
Data Index: 7723296 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.7012. Min Range: -12.7012
Max Act: 10.8262. Min Act: -0.1700
Data Index: 6537836 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.7012. Min Range: -12.7012
Max Act: 10.7012. Min Act: -0.1700
Data Index: 954799 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.7012. Min Range: -12.7012
Max Act: 10.9512. Min Act: -0.1700
Data Index: 3198202 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.7012. Min Range: -12.7012
Max Act: 10.4512. Min Act: -0.1700
Data Index: 7264702 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.7012. Min Range: -12.7012
Max Act: 10.7637. Min Act: -0.1700
Data Index: 8399927 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #19