Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2373 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4441. Min Range: -6.4441
Max Act: 6.4441. Min Act: -0.1700
Data Index: 4287180 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4441. Min Range: -6.4441
Max Act: 6.4441. Min Act: -0.1700
Data Index: 6371544 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4441. Min Range: -6.4441
Max Act: 6.3503. Min Act: -0.1700
Data Index: 3038672 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4441. Min Range: -6.4441
Max Act: 6.2878. Min Act: -0.1700
Data Index: 6520747 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4441. Min Range: -6.4441
Max Act: 6.2566. Min Act: -0.1700
Data Index: 6360576 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4441. Min Range: -6.4441
Max Act: 6.2253. Min Act: -0.1700
Data Index: 7908657 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4441. Min Range: -6.4441
Max Act: 6.2253. Min Act: -0.1700
Data Index: 4366715 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4441. Min Range: -6.4441
Max Act: 6.1941. Min Act: -0.1700
Data Index: 6793876 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4441. Min Range: -6.4441
Max Act: 6.1628. Min Act: -0.1700
Data Index: 6765299 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4441. Min Range: -6.4441
Max Act: 6.1316. Min Act: -0.1700
Data Index: 3215920 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4441. Min Range: -6.4441
Max Act: 6.1003. Min Act: -0.1700
Data Index: 3490193 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4441. Min Range: -6.4441
Max Act: 6.1003. Min Act: -0.1700
Data Index: 2916246 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4441. Min Range: -6.4441
Max Act: 6.1003. Min Act: -0.1700
Data Index: 459262 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4441. Min Range: -6.4441
Max Act: 6.0691. Min Act: -0.1700
Data Index: 6339221 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4441. Min Range: -6.4441
Max Act: 6.0691. Min Act: -0.1700
Data Index: 8111106 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4441. Min Range: -6.4441
Max Act: 6.0378. Min Act: -0.1700
Data Index: 2226361 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4441. Min Range: -6.4441
Max Act: 6.0378. Min Act: -0.1700
Data Index: 8376299 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4441. Min Range: -6.4441
Max Act: 6.0066. Min Act: -0.1700
Data Index: 577910 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4441. Min Range: -6.4441
Max Act: 5.9753. Min Act: -0.1700
Data Index: 1400621 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4441. Min Range: -6.4441
Max Act: 5.9753. Min Act: -0.1700
Data Index: 4376813 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19