Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 578 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5905. Min Range: -4.5905
Max Act: 4.5905. Min Act: -0.1700
Data Index: 1389379 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5905. Min Range: -4.5905
Max Act: 4.5280. Min Act: -0.1700
Data Index: 2215134 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5905. Min Range: -4.5905
Max Act: 4.4967. Min Act: -0.1700
Data Index: 6466146 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5905. Min Range: -4.5905
Max Act: 4.4655. Min Act: -0.1700
Data Index: 4325871 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5905. Min Range: -4.5905
Max Act: 4.4655. Min Act: -0.1700
Data Index: 2607762 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5905. Min Range: -4.5905
Max Act: 4.4655. Min Act: -0.1700
Data Index: 1827507 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5905. Min Range: -4.5905
Max Act: 4.4030. Min Act: -0.1700
Data Index: 3344213 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5905. Min Range: -4.5905
Max Act: 4.4030. Min Act: -0.1700
Data Index: 8351751 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5905. Min Range: -4.5905
Max Act: 4.4030. Min Act: -0.1700
Data Index: 2373738 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5905. Min Range: -4.5905
Max Act: 4.3717. Min Act: -0.1700
Data Index: 6997779 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5905. Min Range: -4.5905
Max Act: 4.3405. Min Act: -0.1700
Data Index: 6885984 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5905. Min Range: -4.5905
Max Act: 4.3405. Min Act: -0.1700
Data Index: 731624 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5905. Min Range: -4.5905
Max Act: 4.3405. Min Act: -0.1700
Data Index: 8284400 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5905. Min Range: -4.5905
Max Act: 4.3405. Min Act: -0.1700
Data Index: 2000181 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5905. Min Range: -4.5905
Max Act: 4.3405. Min Act: -0.1700
Data Index: 6986884 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5905. Min Range: -4.5905
Max Act: 4.3092. Min Act: -0.1700
Data Index: 6986899 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5905. Min Range: -4.5905
Max Act: 4.3092. Min Act: -0.1700
Data Index: 6458448 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5905. Min Range: -4.5905
Max Act: 4.2780. Min Act: -0.1700
Data Index: 5103085 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5905. Min Range: -4.5905
Max Act: 4.3092. Min Act: -0.1700
Data Index: 4094212 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5905. Min Range: -4.5905
Max Act: 4.2780. Min Act: -0.1700
Data Index: 4202258 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19