Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1786 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9200. Min Range: -6.9200
Max Act: 6.9200. Min Act: -0.1700
Data Index: 1050495 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9200. Min Range: -6.9200
Max Act: 6.5762. Min Act: -0.1700
Data Index: 2471264 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9200. Min Range: -6.9200
Max Act: 6.5762. Min Act: -0.1700
Data Index: 8456522 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9200. Min Range: -6.9200
Max Act: 6.6075. Min Act: -0.1700
Data Index: 6673423 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9200. Min Range: -6.9200
Max Act: 6.4825. Min Act: -0.1700
Data Index: 8468660 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9200. Min Range: -6.9200
Max Act: 6.5137. Min Act: -0.1700
Data Index: 238078 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9200. Min Range: -6.9200
Max Act: 6.3262. Min Act: -0.1700
Data Index: 3412420 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9200. Min Range: -6.9200
Max Act: 6.2950. Min Act: -0.1700
Data Index: 8575744 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9200. Min Range: -6.9200
Max Act: 6.2950. Min Act: -0.1700
Data Index: 2339307 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9200. Min Range: -6.9200
Max Act: 6.2950. Min Act: -0.1700
Data Index: 7242693 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9200. Min Range: -6.9200
Max Act: 6.3575. Min Act: -0.1700
Data Index: 125579 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9200. Min Range: -6.9200
Max Act: 6.2325. Min Act: -0.1700
Data Index: 7551565 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9200. Min Range: -6.9200
Max Act: 6.3262. Min Act: -0.1700
Data Index: 4779553 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9200. Min Range: -6.9200
Max Act: 6.2012. Min Act: -0.1700
Data Index: 3114222 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9200. Min Range: -6.9200
Max Act: 6.2012. Min Act: -0.1700
Data Index: 435381 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9200. Min Range: -6.9200
Max Act: 6.1700. Min Act: -0.1700
Data Index: 2573146 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9200. Min Range: -6.9200
Max Act: 6.2012. Min Act: -0.1700
Data Index: 5918452 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9200. Min Range: -6.9200
Max Act: 6.1700. Min Act: -0.1700
Data Index: 6067332 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9200. Min Range: -6.9200
Max Act: 6.1700. Min Act: -0.1700
Data Index: 635025 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9200. Min Range: -6.9200
Max Act: 6.1700. Min Act: -0.1700
Data Index: 4724506 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19