Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2533 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6913. Min Range: -6.6913
Max Act: 6.6913. Min Act: -0.1700
Data Index: 3500432 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6913. Min Range: -6.6913
Max Act: 6.5975. Min Act: -0.1700
Data Index: 5808723 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6913. Min Range: -6.6913
Max Act: 6.5663. Min Act: -0.1700
Data Index: 3456682 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6913. Min Range: -6.6913
Max Act: 6.5038. Min Act: -0.1700
Data Index: 6178129 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6913. Min Range: -6.6913
Max Act: 6.4413. Min Act: -0.1700
Data Index: 2198986 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6913. Min Range: -6.6913
Max Act: 6.4413. Min Act: -0.1700
Data Index: 5204515 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6913. Min Range: -6.6913
Max Act: 6.4100. Min Act: -0.1700
Data Index: 5931001 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6913. Min Range: -6.6913
Max Act: 6.3788. Min Act: -0.1700
Data Index: 4894493 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6913. Min Range: -6.6913
Max Act: 6.3163. Min Act: -0.1700
Data Index: 774560 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6913. Min Range: -6.6913
Max Act: 6.3163. Min Act: -0.1700
Data Index: 2494239 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6913. Min Range: -6.6913
Max Act: 6.2850. Min Act: -0.1700
Data Index: 417973 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6913. Min Range: -6.6913
Max Act: 6.3163. Min Act: -0.1700
Data Index: 6210807 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6913. Min Range: -6.6913
Max Act: 6.2850. Min Act: -0.1700
Data Index: 1622649 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6913. Min Range: -6.6913
Max Act: 6.2538. Min Act: -0.1700
Data Index: 8710715 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6913. Min Range: -6.6913
Max Act: 6.2538. Min Act: -0.1700
Data Index: 7585732 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6913. Min Range: -6.6913
Max Act: 6.2538. Min Act: -0.1700
Data Index: 70233 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6913. Min Range: -6.6913
Max Act: 6.2850. Min Act: -0.1700
Data Index: 2076068 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6913. Min Range: -6.6913
Max Act: 6.2225. Min Act: -0.1700
Data Index: 7376116 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6913. Min Range: -6.6913
Max Act: 6.2225. Min Act: -0.1700
Data Index: 5482000 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6913. Min Range: -6.6913
Max Act: 6.1913. Min Act: -0.1700
Data Index: 2595189 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19