Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1909 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.4755. Min Act: -0.1700
Data Index: 5558929 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.4598. Min Act: -0.1700
Data Index: 1640824 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.3815. Min Act: -0.1700
Data Index: 4336988 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.3658. Min Act: -0.1700
Data Index: 5444531 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.3187. Min Act: -0.1700
Data Index: 1118488 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.3344. Min Act: -0.1700
Data Index: 609679 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.3187. Min Act: -0.1700
Data Index: 3316459 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.3030. Min Act: -0.1700
Data Index: 1023065 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.2559. Min Act: -0.1700
Data Index: 7033760 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.2559. Min Act: -0.1700
Data Index: 1311221 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.2245. Min Act: -0.1700
Data Index: 1143971 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.2245. Min Act: -0.1700
Data Index: 588221 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.1930. Min Act: -0.1700
Data Index: 4585377 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.1930. Min Act: -0.1700
Data Index: 4441876 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.1930. Min Act: -0.1700
Data Index: 5751338 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.1773. Min Act: -0.1700
Data Index: 364520 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.1773. Min Act: -0.1700
Data Index: 2490802 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.1616. Min Act: -0.1700
Data Index: 4613006 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.1773. Min Act: -0.1700
Data Index: 2656434 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.1458. Min Act: -0.1700
Data Index: 3613080 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19